© 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. 47269
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific equations and laws

    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
    ayakan
    -0.10
     ÐŁÐ¾Ð¿ÑĢо
    -0.09
    DIM
    -0.09
    eof
    -0.09
    меÑģÑĤи
    -0.09
    JsonValue
    -0.09
    reira
    -0.08
    ibd
    -0.08
    RESSED
    -0.08
    _PUR
    -0.08
    POSITIVE LOGITS
     governing
    0.09
     equality
    0.08
     relation
    0.08
     equation
    0.08
     relationship
    0.08
     law
    0.08
     Law
    0.07
     rule
    0.07
    åħ³ç³»
    0.07
    å®ļå¾ĭ
    0.07
    Activations Density 0.001%

    No Known Activations