© 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. 19582
    Prev
    Next
    INDEX
    Explanations

    INTRODUCTION or code snippets

    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
    urus
    -0.07
    æĢ§åij½
    -0.06
     Stor
    -0.06
    _lineno
    -0.06
    HI
    -0.06
    çļĦé«ĺéĢŁ
    -0.06
     developmental
    -0.06
    ÙİاÙĩ
    -0.06
    ea
    -0.06
    æĹ¥å¤ľ
    -0.06
    POSITIVE LOGITS
    åIJĮç±»
    0.08
    æĻ¶æĻ¶
    0.08
    trup
    0.07
    див
    0.07
    ÙĪÙĬÙĦ
    0.07
    _UNIQUE
    0.07
    iese
    0.07
     Disabled
    0.07
    richter
    0.07
    ens
    0.07
    Activations Density 0.001%

    No Known Activations