© 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. 47843
    Prev
    Next
    INDEX
    Explanations

    journal citations with numerical identifiers

    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
    ly
    -0.06
    ley
    -0.06
    izon
    -0.06
    å¿ĥçIJĨä¸Ĭ
    -0.06
    pu
    -0.06
     ant
    -0.06
    ç»ı管
    -0.05
    пÑĥлÑĮ
    -0.05
    los
    -0.05
    #{
    -0.05
    POSITIVE LOGITS
    éĵ¿
    0.08
    æĹ¥èĩ³
    0.08
    ocate
    0.08
    æī¬æī¬
    0.08
    ?-
    0.08
     resourceName
    0.08
    æıļ
    0.08
    ocial
    0.07
     ÙĤÙĦت
    0.07
    ickets
    0.07
    Activations Density 0.046%

    No Known Activations