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. 27411
    Prev
    Next
    INDEX
    Explanations

    was

    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_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
    oline
    -0.07
    :String
    -0.07
    党的建设
    -0.07
    ㄴ
    -0.07
    猷
    -0.07
     TimeZone
    -0.06
     באות
    -0.06
    getStyle
    -0.06
    郿
    -0.06
    \Page
    -0.06
    POSITIVE LOGITS
    Acknowled
    0.08
     improbable
    0.07
    惦
    0.07
     manipulate
    0.07
     McA
    0.07
     balancing
    0.07
    夹
    0.07
    HEL
    0.07
     Anita
    0.07
    @endsection
    0.07
    Activations Density 0.037%

    No Known Activations