© 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. 21397
    Prev
    Next
    INDEX
    Explanations

    selected elements/fields/subset

    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
    ä¸įèĥľ
    -0.07
    หรีà¹Ī
    -0.07
    Hum
    -0.07
    çĪ¸å¦Ī
    -0.07
     hum
    -0.07
    oce
    -0.07
     cár
    -0.07
     salah
    -0.07
    uno
    -0.07
    hey
    -0.06
    POSITIVE LOGITS
    æľīéĻIJ
    0.09
    æľīéĻIJçļĦ
    0.09
     subset
    0.09
     full
    0.08
    subset
    0.08
     restriction
    0.08
     confined
    0.08
     limited
    0.08
    illon
    0.07
    åĴĮæľī
    0.07
    Activations Density 0.172%

    No Known Activations