© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    11. 109264
    Prev
    Next
    INDEX
    Explanations

    wisdom

    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
    ltre
    -0.07
     Lease
    -0.07
     COURT
    -0.07
    Lock
    -0.07
    itz
    -0.07
    ouple
    -0.07
    lok
    -0.07
    court
    -0.07
     squeeze
    -0.07
     enjo
    -0.07
    POSITIVE LOGITS
     הד
    0.08
    客戶
    0.07
     דיגיט
    0.07
    领域的
    0.07
    苏州
    0.07
    增值服务
    0.07
    鬼
    0.07
    须
    0.07
     wisdom
    0.07
     الدنيا
    0.07
    Activations Density 0.011%

    No Known Activations