© 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. 25187
    Prev
    Next
    INDEX
    Explanations

    m followed by a noun

    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
    ¹
    -0.07
    полÑĮ
    -0.07
    ing
    -0.07
    elig
    -0.07
    æīĵæī®
    -0.06
     and
    -0.06
    odont
    -0.06
    erii
    -0.06
    à¹ĥà¸Ī
    -0.06
    xCD
    -0.06
    POSITIVE LOGITS
    apped
    0.08
    icer
    0.07
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.07
     karÅŁ
    0.07
    è¿ĻéĩĮéĥ½æľī
    0.07
    pps
    0.07
    边走
    0.07
    bies
    0.07
     Postar
    0.07
    áĥ«
    0.07
    Activations Density 0.130%

    No Known Activations