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. 25001
    Prev
    Next
    INDEX
    Explanations

    French language

    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
    [,
    -0.07
    選擇
    -0.07
    吸收
    -0.07
    order
    -0.07
     wave
    -0.07
    ア
    -0.07
    ויד
    -0.07
    相爱
    -0.07
    坐
    -0.07
    经
    -0.07
    POSITIVE LOGITS
     newline
    0.08
     בין
    0.08
     الإنس
    0.07
     NYC
    0.07
     cartoon
    0.07
    _characters
    0.07
     notifier
    0.07
    Präs
    0.07
    _titles
    0.07
    .UserInfo
    0.07
    Activations Density 0.028%

    No Known Activations