© 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. 16965
    Prev
    Next
    INDEX
    Explanations

    departures and departures

    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
    ike
    -0.08
    vey
    -0.07
    çļĦåĩºçİ°
    -0.07
    è¿ĻæľŁéĹ´
    -0.07
    ihan
    -0.07
    Ỽp
    -0.07
    ä¸Ģ度çļĦ
    -0.07
    ieme
    -0.07
    orus
    -0.07
    ativamente
    -0.07
    POSITIVE LOGITS
    retty
    0.08
    igny
    0.07
    echa
    0.07
    خاذ
    0.07
    sWith
    0.07
    ׳ק
    0.07
    ãģ¾ãģĻ
    0.07
    ä¸įä¹ħçļĦ
    0.07
    สูà¹Ī
    0.07
    ively
    0.07
    Activations Density 0.007%

    No Known Activations