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. 11-RESID-POST-AA
    6. 23156
    Prev
    Next
    INDEX
    Explanations

    lethal

    np_max-act · gemini-2.0-flash
    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
     Malone
    -0.07
    _Selected
    -0.07
     מ
    -0.07
    RoutingModule
    -0.07
    ☃
    -0.06
     busy
    -0.06
    onents
    -0.06
    (describing
    -0.06
     świe
    -0.06
     cáo
    -0.06
    POSITIVE LOGITS
    ll
    0.07
     predicate
    0.07
    pn
    0.07
     viable
    0.07
     politically
    0.07
    /auth
    0.07
    (wp
    0.06
    .ImageField
    0.06
    @yahoo
    0.06
    	length
    0.06
    Activations Density 0.002%

    No Known Activations