© 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. 61346
    Prev
    Next
    INDEX
    Explanations

    parentheses after numbers

    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
    ewan
    -0.09
    anson
    -0.09
    /--
    -0.08
    å¾Ĵ
    -0.08
    gemÃ¤ÃŁ
    -0.07
    个æĸ¹éĿ¢
    -0.07
    ewa
    -0.07
    å½·
    -0.07
    æµ·é»ĺ
    -0.07
    ather
    -0.07
    POSITIVE LOGITS
    åĬŁ
    0.06
    大åĬŁ
    0.06
    æľīåĬŁ
    0.06
     decom
    0.06
    _WRAP
    0.06
     scare
    0.06
    _OID
    0.06
    indi
    0.06
    æĭĨ解
    0.06
    ืà¹Īà¸Ļ
    0.06
    Activations Density 0.006%

    No Known Activations