© 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. 27660
    Prev
    Next
    INDEX
    Explanations

    relative to each other

    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
    轻轻æĿ¾
    -0.09
    estead
    -0.08
    ä¸ī人
    -0.08
    åĽĽéĢļ
    -0.08
    FromString
    -0.08
    Singleton
    -0.08
    èĭij
    -0.08
    æĹłè®ºä»İ
    -0.07
    ä¸įåıĹ
    -0.07
     thon
    -0.07
    POSITIVE LOGITS
     adjoining
    0.08
     amalg
    0.07
    夹
    0.07
    沿çĿĢ
    0.06
     rabat
    0.06
    两éĿ¢
    0.06
    adat
    0.06
    夹å±Ĥ
    0.06
    Subtitle
    0.06
    沿
    0.06
    Activations Density 0.001%

    No Known Activations