© 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. 12845
    Prev
    Next
    INDEX
    Explanations

    normalization and renormalization

    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
    ote
    -0.08
    åľ¨å¿ħ
    -0.08
    Äĥn
    -0.07
    باÙĨ
    -0.07
    inct
    -0.07
    窩
    -0.07
    omotor
    -0.07
    æīģ
    -0.07
     overridden
    -0.07
    ross
    -0.07
    POSITIVE LOGITS
    izable
    0.08
    atively
    0.08
    ä¸įæĭĶ
    0.07
    çļĦåIJĦ项
    0.07
    abel
    0.07
    æľŁåĨħ
    0.07
    éĩįãģŃ
    0.06
    uges
    0.06
    /reg
    0.06
    аÑģа
    0.06
    Activations Density 0.002%

    No Known Activations