© 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. 20211
    Prev
    Next
    INDEX
    Explanations

    ordering by maximum or decreasing

    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
     costs
    -0.08
     heavier
    -0.08
     burden
    -0.08
    æĪIJæľ¬
    -0.07
     ë¶Ģëĭ´
    -0.07
    cost
    -0.07
     cost
    -0.07
     burdens
    -0.07
     required
    -0.07
    è´Łæĭħ
    -0.07
    POSITIVE LOGITS
    æľĢ大åĮĸ
    0.14
     maximizing
    0.13
     Maxim
    0.13
     maxim
    0.13
     maximize
    0.12
    -max
    0.11
    Max
    0.10
     maximal
    0.10
     макÑģ
    0.10
    max
    0.10
    Activations Density 0.043%

    No Known Activations