© 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. 62389
    Prev
    Next
    INDEX
    Explanations

    symbols and chemical formulas

    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
    ins
    -0.07
    é£İåIJ¹
    -0.07
    ánt
    -0.07
    _BASIC
    -0.06
     /^\
    -0.06
    leck
    -0.06
     ׾פ׳×Ļ
    -0.06
     oka
    -0.06
    ETCH
    -0.06
    eld
    -0.06
    POSITIVE LOGITS
    _pow
    0.08
    untime
    0.08
     Ress
    0.07
    ipto
    0.07
    į¨
    0.07
    andom
    0.07
    diyy
    0.07
    缴è¨Ģ
    0.07
     ê·¸ë¦¬ê³ł
    0.07
    ´Ī
    0.07
    Activations Density 0.015%

    No Known Activations