© 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. 60151
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation

    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
    Ĺ
    -0.09
     Mohamm
    -0.06
    à°¾
    -0.06
    ets
    -0.06
    ãģĹãģıãģ¯
    -0.06
    лиз
    -0.06
    Ľ
    -0.06
    ../../
    -0.06
    ov
    -0.06
    haps
    -0.06
    POSITIVE LOGITS
    enhagen
    0.08
     ...\
    0.08
     Ñģно
    0.07
    ardt
    0.07
    entication
    0.07
    shal
    0.07
    ajem
    0.07
    ktan
    0.07
    ণ
    0.07
    INGTON
    0.07
    Activations Density 0.003%

    No Known Activations