© 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. 56033
    Prev
    Next
    INDEX
    Explanations

    import java classes

    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
    inning
    -0.07
    fol
    -0.06
    ield
    -0.06
    nets
    -0.06
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.06
    nun
    -0.06
    è°Ĭ
    -0.06
    ä¿ĺ
    -0.06
    .netflix
    -0.06
    iel
    -0.06
    POSITIVE LOGITS
    Compat
    0.08
    åŃIJæĽ°
    0.08
    دار
    0.07
    สà¹Īวà¸Ļ
    0.07
    nodoc
    0.07
    तà¥įरà¥Ģ
    0.07
    кла
    0.07
    å·¥ç¨ĭåѦéĻ¢
    0.07
    lese
    0.07
    Reader
    0.07
    Activations Density 0.056%

    No Known Activations