© 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. 20208
    Prev
    Next
    INDEX
    Explanations

    prize money

    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
    itz
    -0.07
    inci
    -0.07
     STDMETHODCALLTYPE
    -0.07
    api
    -0.07
    詩
    -0.07
    投资者
    -0.06
     scientists
    -0.06
    想像
    -0.06
     form
    -0.06
    引力
    -0.06
    POSITIVE LOGITS
    .dgv
    0.07
     rew
    0.07
    during
    0.07
     ADDR
    0.07
    .':
    0.07
    typically
    0.07
    _'
    0.07
     errores
    0.07
     weekends
    0.07
    _NB
    0.06
    Activations Density 0.010%

    No Known Activations