Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 86260
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash

    Instances of a question opening in the "How do I ..." form (i.e., the interrogative phrase that asks for instructions).

    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
     corner
    -0.07
    stinian
    -0.07
    locs
    -0.07
    تعيين
    -0.07
    😷
    -0.07
    选择
    -0.06
     않는
    -0.06
     Mug
    -0.06
    migration
    -0.06
     Achie
    -0.06
    POSITIVE LOGITS
    	So
    0.07
    法
    0.07
    .Red
    0.07
    _PRODUCT
    0.07
    骨
    0.07
     advisors
    0.07
     OFF
    0.06
    [param
    0.06
     kết
    0.06
    Dimension
    0.06
    Activations Density 0.034%

    No Known Activations