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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12033
    Prev
    Next
    INDEX
    Explanations

    places and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CIAL
    -0.07
    渡è¿ĩ
    -0.07
    YE
    -0.07
    urz
    -0.07
    ä¸ĢéĢļ
    -0.07
    ä¸ī段
    -0.07
     วิ
    -0.07
    asures
    -0.07
     mold
    -0.06
     FK
    -0.06
    POSITIVE LOGITS
    alto
    0.07
    apus
    0.07
    åħ¨ç¾İ
    0.07
    acos
    0.07
     Charger
    0.06
    人äºĭ
    0.06
    èĵī
    0.06
    صب
    0.06
    forth
    0.06
    MimeType
    0.06
    Activations Density 0.339%

    No Known Activations