© 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. 31115
    Prev
    Next
    INDEX
    Explanations

    may be responsible

    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
    ä¸įèĥ½åľ¨
    -0.07
    anon
    -0.07
    enor
    -0.07
    меÑĤи
    -0.07
    åĪĨéĻ¢
    -0.07
    æŀľ
    -0.07
    _BAR
    -0.07
    wal
    -0.07
    å§Ĩæĸ¯
    -0.07
    ited
    -0.06
    POSITIVE LOGITS
    onna
    0.08
    ä¸Ĭæĸ°åı°éĺ¶
    0.07
    cience
    0.07
    æĶ¾çŁ¢
    0.07
    åķ¥
    0.07
    abh
    0.07
    avage
    0.07
     лÑĥÑĩ
    0.06
    å¾Ĭ
    0.06
    驾é©Ń
    0.06
    Activations Density 0.616%

    No Known Activations