© 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. 28148
    Prev
    Next
    INDEX
    Explanations

    incorporated by reference

    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
    mani
    -0.06
    (:,:,
    -0.06
    gon
    -0.06
    æĹłè¾ľ
    -0.06
     Soros
    -0.06
    hiba
    -0.06
    chim
    -0.06
    Kir
    -0.06
    åĽŀäºĨ
    -0.06
    _INTERRUPT
    -0.06
    POSITIVE LOGITS
    ä¸Ģ页
    0.08
    ç»ĨåĪĻ
    0.08
    ipel
    0.08
    æĸ°åºĹ
    0.07
    å®ŀæĸ½ç»ĨåĪĻ
    0.07
    å¦Ĥæŀľä½łè§īå¾Ĺ
    0.07
    chers
    0.07
    lott
    0.07
     partes
    0.07
     authorised
    0.07
    Activations Density 0.060%

    No Known Activations