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. 11-RESID-POST-AA
    6. 25879
    Prev
    Next
    INDEX
    Explanations

    matrices and equations

    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
    干嘛
    -0.08
    ि�
    -0.08
    瘆
    -0.07
    Wi
    -0.07
    偰
    -0.07
    ignore
    -0.07
     Easily
    -0.07
    undred
    -0.07
    watch
    -0.07
     prescriptions
    -0.07
    POSITIVE LOGITS
    协办
    0.07
     EM
    0.07
     defect
    0.07
    ととも
    0.07
    VIDEO
    0.07
    才是真正
    0.07
    袢
    0.06
    읐
    0.06
    oused
    0.06
    シリーズ
    0.06
    Activations Density 0.018%

    No Known Activations