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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 44768
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    It detects sentence-beginning tokens—especially initial pronouns, articles or other capitalized/discourse words that start a user or system utterance.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝄅
    -0.08
    ��
    -0.07
     emerging
    -0.07
     pageInfo
    -0.07
     particularly
    -0.07
    ㄥ
    -0.07
     repetition
    -0.07
    ritch
    -0.07
     impeachment
    -0.07
     halves
    -0.06
    POSITIVE LOGITS
     ;↵
    0.07
    _clean
    0.07
    legend
    0.06
    '],['
    0.06
    .sum
    0.06
    >.↵
    0.06
    ꪕ
    0.06
     ;↵↵↵
    0.06
    cmds
    0.06
    沟通
    0.06
    Activations Density 0.154%

    No Known Activations