© 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. 18246
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and fractions

    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
    erra
    -0.08
    tvr
    -0.07
    yron
    -0.07
    ä¸ŃåĽ½åĽ½å®¶
    -0.07
    ynd
    -0.07
    icali
    -0.06
    enhagen
    -0.06
    ern
    -0.06
    QUOTE
    -0.06
     /^(
    -0.06
    POSITIVE LOGITS
    æĺ¯åħ¶
    0.07
    .bel
    0.07
    halter
    0.07
    appel
    0.07
    .loc
    0.07
    agas
    0.07
     coquine
    0.06
    _CHO
    0.06
    elight
    0.06
    袱
    0.06
    Activations Density 0.006%

    No Known Activations