© 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. 34789
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
    anska
    -0.07
    .zip
    -0.07
    åĴ«
    -0.06
     intric
    -0.06
    为äºĨä¿ĿæĬ¤
    -0.06
     act
    -0.06
     acts
    -0.06
    mary
    -0.06
     hei
    -0.06
    é£ŀæī¬
    -0.06
    POSITIVE LOGITS
    اعد
    0.08
    nbr
    0.08
    ục
    0.08
    íľĺ
    0.08
    æĥŁ
    0.07
    apan
    0.07
    иа
    0.07
    komsten
    0.07
    apy
    0.07
    //-
    0.07
    Activations Density 0.004%

    No Known Activations