© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44882
    Prev
    Next
    INDEX
    Explanations

    from 0 to infinity

    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
    ly
    -0.08
    est
    -0.07
    èįĨæ£ĺ
    -0.06
    åIJĪè®®åºŃ
    -0.06
    åĦ¿
    -0.06
    ç²¾
    -0.06
    arr
    -0.06
     Miranda
    -0.06
    å¤įåĪ¶æĪĸ
    -0.06
    by
    -0.06
    POSITIVE LOGITS
    TOTYPE
    0.08
    èĵĿåŃĹ
    0.08
    ä¸įæŃ»
    0.08
    µ
    0.08
    _RADIO
    0.08
    jonal
    0.08
    otify
    0.07
    ierre
    0.07
    ollo
    0.07
    efeld
    0.07
    Activations Density 0.002%

    No Known Activations