© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58152
    Prev
    Next
    INDEX
    Explanations

    Original Message

    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
    èĸ
    -0.08
    agam
    -0.07
    ä¸Ĭ天
    -0.07
    æ½Ķ
    -0.07
     мÑı
    -0.06
     petty
    -0.06
    unga
    -0.06
    ×ĺ×Ķ
    -0.06
    æľĿå¤ķ
    -0.06
    å¿ħæľī
    -0.06
    POSITIVE LOGITS
    以ä¸Ģ
    0.07
    itata
    0.06
    ikkert
    0.06
    è¾ľ
    0.06
     mer
    0.06
    æĪijåĽŃ
    0.06
    ogr
    0.06
    Ī
    0.06
    æij©æł¹
    0.06
    ç²¾ç¥ŀä¸Ĭ
    0.06
    Activations Density 0.036%

    No Known Activations