© 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. 11651
    Prev
    Next
    INDEX
    Explanations

    React, extension, functions, products

    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
    ÙĦÙĬ
    -0.07
    ropolis
    -0.07
    ä¾Ľ
    -0.07
    tabil
    -0.07
     cons
    -0.07
    ÑĦÑĢа
    -0.07
    à¸Ħูà¹Ī
    -0.06
    .cr
    -0.06
    åĽ
    -0.06
    åı¯æ¢¦
    -0.06
    POSITIVE LOGITS
    ERI
    0.08
    ìĪ¨
    0.07
    HOOK
    0.07
    è·¯åŃIJ
    0.07
    GV
    0.07
    èĪį
    0.07
    ISTER
    0.06
    èĪİ
    0.06
     DeepCopy
    0.06
    éĢ¢
    0.06
    Activations Density 0.336%

    No Known Activations