© 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
    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. 25810
    Prev
    Next
    INDEX
    Explanations

    Astronomical objects and numbers

    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
     Testament
    -0.07
    AuthService
    -0.07
    底层
    -0.07
    一层
    -0.07
    Pattern
    -0.07
    avian
    -0.07
    候
    -0.07
    paralleled
    -0.06
    Answers
    -0.06
     dispon
    -0.06
    POSITIVE LOGITS
    꽥
    0.07
    _Err
    0.07
    _MATRIX
    0.07
    refs
    0.06
    -master
    0.06
    /dom
    0.06
    揍
    0.06
     Each
    0.06
    ℗
    0.06
    咧
    0.06
    Activations Density 0.010%

    No Known Activations