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. 11-RESID-POST-AA
    6. 87125
    Prev
    Next
    INDEX
    Explanations

    sentences

    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
    .setGeometry
    -0.07
     độc
    -0.07
    уд
    -0.07
    참
    -0.06
     क
    -0.06
    嗟
    -0.06
    網友
    -0.06
     convo
    -0.06
     Prevention
    -0.06
    _Two
    -0.06
    POSITIVE LOGITS
     Classified
    0.07
    פופולרי
    0.07
    mode
    0.07
     refreshToken
    0.07
    京津
    0.07
     hablar
    0.07
    cheap
    0.07
    不稳定
    0.07
    Yellow
    0.07
    contenido
    0.07
    Activations Density 0.206%

    No Known Activations