© 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. 37801
    Prev
    Next
    INDEX
    Explanations

    items, places, or conditions

    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
    诸å¦Ĥ
    -0.08
    æĢ
    -0.08
     ëĭ¨ëıħ
    -0.07
    opportun
    -0.07
    avenport
    -0.07
    为è¾ħ
    -0.07
    è¯Ĭ
    -0.07
    erti
    -0.07
    以ä¸ĭåĩłç§į
    -0.07
    habil
    -0.07
    POSITIVE LOGITS
    åīįå¤ķ
    0.07
    ãģ®ãĤĪãģĨãģ«
    0.07
    çŃīé¢ĨåŁŁ
    0.07
    çŃīè¡Įä¸ļ
    0.06
    zig
    0.06
     Ever
    0.06
    çŃīåľºæīĢ
    0.06
    åģ¿
    0.06
     Ðĺго
    0.06
    çŃīé¢ĨåŁŁçļĦ
    0.06
    Activations Density 0.065%

    No Known Activations