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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 21329
    Prev
    Next
    INDEX
    Explanations

    How

    np_max-act · gemini-2.0-flash

    Questions that begin with the word "How" (i.e., sentence-initial "How" question openings).

    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
    屬於
    -0.07
    _origin
    -0.07
     similarities
    -0.07
    莽
    -0.07
    瞄准
    -0.06
     allow
    -0.06
     Rank
    -0.06
    Assigned
    -0.06
    分辨
    -0.06
     LOD
    -0.06
    POSITIVE LOGITS
    Flex
    0.07
     invokevirtual
    0.07
    ڴ
    0.07
     iterators
    0.06
    _RAM
    0.06
     وأضاف
    0.06
    검
    0.06
    unprocessable
    0.06
    BER
    0.06
    Mount
    0.06
    Activations Density 0.065%

    No Known Activations