© 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. 929
    Prev
    Next
    INDEX
    Explanations

    expressions with mathematical 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
    ongi
    -0.09
    ceso
    -0.09
    enea
    -0.08
    ento
    -0.08
    ëĿ¼ë§Ī
    -0.08
    edio
    -0.08
    chini
    -0.08
    cula
    -0.08
    esar
    -0.08
    emui
    -0.08
    POSITIVE LOGITS
    Âł
    0.11
    âĢ
    0.07
    lm
    0.07
    ng
    0.07
    ask
    0.07
     B
    0.06
    il
    0.06
     –
    0.06
     ...
    0.06
     D
    0.06
    Activations Density 0.011%

    No Known Activations