© 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. 3841
    Prev
    Next
    INDEX
    Explanations

    code ending punctuation

    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
    lick
    -0.08
    屯
    -0.07
    _INTR
    -0.07
    ellar
    -0.06
    .application
    -0.06
    ellis
    -0.06
    è¾ħ
    -0.06
     Faust
    -0.06
    INAN
    -0.06
    cons
    -0.06
    POSITIVE LOGITS
    ppy
    0.09
    åĸľ
    0.07
    MAND
    0.07
    å¸ľ
    0.07
    å¥½å·¥ä½ľ
    0.07
    _SENT
    0.07
    å¹
    0.07
    ä½Ĩåı¯ä»¥
    0.07
    à¸ĩà¹Īาย
    0.07
    éĢıäºĨ
    0.06
    Activations Density 0.021%

    No Known Activations