Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 2088
    Prev
    Next
    INDEX
    Explanations

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    偌
    -0.07
    .fit
    -0.07
    ','#
    -0.07
    ﭐ
    -0.07
    atypes
    -0.07
    qué
    -0.07
     lawsuit
    -0.07
    社交媒体
    -0.07
    лись
    -0.07
    I
    -0.07
    POSITIVE LOGITS
     PICK
    0.07
     Peek
    0.07
    ȝ
    0.07
    意大利
    0.07
     RegexOptions
    0.07
    codigo
    0.06
    濟
    0.06
    ={{
    0.06
     Geography
    0.06
     historians
    0.06
    Activations Density 0.008%

    No Known Activations