© 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. 62504
    Prev
    Next
    INDEX
    Explanations

    placeholder substitution logic

    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
    hausen
    -0.08
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.07
    éĻ°
    -0.06
    ÑĮÑİ
    -0.06
    undu
    -0.06
    足以
    -0.06
     House
    -0.06
     establish
    -0.06
    INTERNAL
    -0.06
    heim
    -0.06
    POSITIVE LOGITS
    çĪĨ
    0.08
    ivet
    0.08
    æĽ¿æį¢
    0.08
     بذ
    0.08
    à¹Ħà¸Ĥ
    0.07
    brace
    0.07
    详ç»Ĩåľ°åĿĢ
    0.07
     Clarkson
    0.07
    itespace
    0.07
    _here
    0.07
    Activations Density 0.009%

    No Known Activations