© 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. 32669
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    duto
    -0.07
    ,:
    -0.07
    atitis
    -0.06
    {:
    -0.06
    以ä¸ĭæĺ¯ä¸ĢäºĽ
    -0.06
     inciso
    -0.06
    ULATE
    -0.06
    anian
    -0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.06
     -*-
    -0.06
    POSITIVE LOGITS
    éĩĮ没æľī
    0.08
    elar
    0.07
    dden
    0.07
    asser
    0.07
    ocre
    0.07
    å¸ĥæĭī
    0.07
    гл
    0.07
    avail
    0.07
    SPA
    0.07
    æĸ¹æĸ¹éĿ¢
    0.07
    Activations Density 0.004%

    No Known Activations