© 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. 62572
    Prev
    Next
    INDEX
    Explanations

    convert chemical/arterial/financial/signals

    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
    agen
    -0.08
    Äıte
    -0.08
    utri
    -0.08
    æĨ¬
    -0.07
    mie
    -0.07
    èIJ½
    -0.07
    олÑĮ
    -0.07
    ãĤ¦ãĥī
    -0.07
    ãģ
    -0.07
    æĺ¯åIJ¦æŃ£å¸¸
    -0.07
    POSITIVE LOGITS
    /of
    0.07
    rv
    0.06
    ////
    0.06
    /on
    0.06
    òng
    0.06
    ï¸İ
    0.06
    è´¹çŃī
    0.06
    ç½ij讯
    0.06
    /from
    0.06
    ,
    0.06
    Activations Density 0.001%

    No Known Activations