© 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. 11-RESID-POST-AA
    11. 30286
    Prev
    Next
    INDEX
    Explanations

    wall

    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
    原理
    -0.07
     MAIL
    -0.07
    /load
    -0.06
    acency
    -0.06
    条件下
    -0.06
    צא
    -0.06
    iguous
    -0.06
     작성
    -0.06
    ofire
    -0.06
     Güncelle
    -0.06
    POSITIVE LOGITS
    .Bold
    0.07
     Burton
    0.07
     uom
    0.07
     racial
    0.07
    _HANDLER
    0.07
     forte
    0.07
    trainer
    0.06
     Gray
    0.06
    xcf
    0.06
    出自
    0.06
    Activations Density 0.005%

    No Known Activations