© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 484
    Prev
    Next
    INDEX
    Explanations

    and

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    國內
    -0.07
    :message
    -0.07
    -0.06
    woocommerce
    -0.06
    لى
    -0.06
    례
    -0.06
    
    -0.06
    cht
    -0.06
    搠
    -0.06
    重视
    -0.06
    POSITIVE LOGITS
    (pwd
    0.08
     SCP
    0.07
     suspects
    0.07
     impuls
    0.07
     commenc
    0.06
     Scre
    0.06
    人民医院
    0.06
    闪烁
    0.06
     Circle
    0.06
     pequeño
    0.06
    Activations Density 0.000%

    No Known Activations