© 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. 48847
    Prev
    Next
    INDEX
    Explanations

    hoaxes and fabrications

    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
     Pt
    -0.07
     производ
    -0.07
    ಕ
    -0.07
     among
    -0.06
     fet
    -0.06
     overt
    -0.06
     ví
    -0.06
    氓
    -0.06
    低于
    -0.06
    (gulp
    -0.06
    POSITIVE LOGITS
     Rev
    0.08
     BUF
    0.07
    .IsTrue
    0.07
    izons
    0.07
    太快
    0.07
    рупп
    0.07
    تحليل
    0.06
    美容
    0.06
    逭
    0.06
    dür
    0.06
    Activations Density 0.055%

    No Known Activations