© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 67363
    Prev
    Next
    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    The presence of a sentence- or section-initial capitalized definite article (i.e., the lead "The" at the start of an article or paragraph).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    隐瞒
    -0.07
     Mc
    -0.07
     Mitchell
    -0.07
     ↵
    -0.07
     quale
    -0.07
    .....↵↵
    -0.07
    杜绝
    -0.07
     C
    -0.07
    cases
    -0.07
    煤炭
    -0.06
    POSITIVE LOGITS
    痱
    0.07
     disbelief
    0.07
    _addresses
    0.07
    	Buffer
    0.07
     במקרה
    0.07
    重点领域
    0.07
     alignSelf
    0.07
    azaar
    0.06
    _CONTACT
    0.06
     semester
    0.06
    Activations Density 0.066%

    No Known Activations