© 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
    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. 75648
    Prev
    Next
    INDEX
    Explanations

    Repair and maintenance

    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
     الأعمال
    -0.07
    ﴽ
    -0.07
     moc
    -0.06
    }(
    -0.06
    ╲
    -0.06
    认为
    -0.06
    有必要
    -0.06
     Sap
    -0.06
    禁忌
    -0.06
    ắ
    -0.06
    POSITIVE LOGITS
    .condition
    0.07
    率达
    0.07
     imageUrl
    0.07
    _cores
    0.07
    轰
    0.06
     konuşma
    0.06
    URATION
    0.06
    .communication
    0.06
    пал
    0.06
     وغير
    0.06
    Activations Density 0.039%

    No Known Activations