© 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. 934
    Prev
    Next
    INDEX
    Explanations

    Uncategorized miscellaneous items

    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
    áĭ«
    -0.08
    amol
    -0.08
    è¹ĭ
    -0.07
    waran
    -0.07
    è¿ĺ好
    -0.07
    ercul
    -0.07
    åIJijä¸ŃåĽ½
    -0.07
     **¡
    -0.07
     Sist
    -0.07
    Mathf
    -0.07
    POSITIVE LOGITS
     Uncategorized
    0.09
     miscellaneous
    0.07
    engen
    0.07
    è¹
    0.07
     ICT
    0.07
    ict
    0.07
     Miscellaneous
    0.07
    /misc
    0.06
    Misc
    0.06
    misc
    0.06
    Activations Density 0.879%

    No Known Activations