© 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. 51292
    Prev
    Next
    INDEX
    Explanations

    shared or half of something

    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
    обо
    -0.07
    antha
    -0.07
     best
    -0.07
    etas
    -0.07
    igram
    -0.07
    _testing
    -0.07
    åĨĽä¸Ń
    -0.07
    å¤įåIJĪåŀĭ
    -0.07
    éĹ²çĿĢ
    -0.06
    é«ĺçħ§
    -0.06
    POSITIVE LOGITS
    shared
    0.09
    /shared
    0.09
    åįĬåĪĨ
    0.09
    -contrib
    0.08
    (shared
    0.08
    åĽłåŃIJ
    0.08
    åĪĨæĭħ
    0.08
    ç»Ļ大家åĪĨ享
    0.08
    åĽĽåĪĨ
    0.08
     shared
    0.08
    Activations Density 0.006%

    No Known Activations