© 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. 34605
    Prev
    Next
    INDEX
    Explanations

    numbers near decimals

    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
    ewood
    -0.08
    OSA
    -0.08
    |%
    -0.08
    èļĤ
    -0.07
    urances
    -0.07
    /etc
    -0.07
    ÏĢάν
    -0.07
    æĹ¥éŁ©
    -0.07
    èĤª
    -0.07
    è²ī
    -0.07
    POSITIVE LOGITS
     validating
    0.07
    irão
    0.06
    alie
    0.06
    æĢħ
    0.06
    vente
    0.06
    ective
    0.06
    ÃŃti
    0.06
     meno
    0.06
    _validation
    0.06
    æ£ĢéªĮ
    0.06
    Activations Density 0.016%

    No Known Activations