© 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. 62768
    Prev
    Next
    INDEX
    Explanations

    file extensions and code constructs

    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
    åĩºäºĨéĹ®é¢ĺ
    -0.07
    ØŃت
    -0.07
    abora
    -0.06
     suivant
    -0.06
    antro
    -0.06
    /apt
    -0.06
    leck
    -0.06
    ceeded
    -0.06
    cest
    -0.06
    ื
    -0.06
    POSITIVE LOGITS
    åħ¬å¼ı
    0.08
    趣
    0.08
    èµĸ
    0.07
    formula
    0.07
    _EOL
    0.07
    åį¿
    0.07
     ÑĢазвеÑĢ
    0.07
     formula
    0.07
     formule
    0.07
    å±ĬæŶ
    0.07
    Activations Density 0.001%

    No Known Activations