© 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. 25881
    Prev
    Next
    INDEX
    Explanations

    fiber regeneration

    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
    ppi
    -0.07
    ãģ£ãģ·
    -0.07
    ä¸į欲
    -0.07
    ç¥IJ
    -0.07
    ki
    -0.07
     unt
    -0.07
    IBE
    -0.06
    #!
    -0.06
    (platform
    -0.06
    ç§ĭ鼨
    -0.06
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģ项
    0.10
    -related
    0.08
    -themed
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    ä¸İåIJ¦
    0.08
    -specific
    0.08
    èµĸ以
    0.07
    uesa
    0.07
    -associated
    0.07
    agos
    0.07
    Activations Density 0.035%

    No Known Activations