© 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. 64742
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    igni
    -0.07
    üter
    -0.07
    sek
    -0.07
    ,',
    -0.07
    对æĤ£èĢħ
    -0.07
    iston
    -0.07
    ,",
    -0.07
    _',
    -0.07
    ARRIER
    -0.07
    ãĥĭãĥĥãĤ¯
    -0.07
    POSITIVE LOGITS
    åģļ好äºĨ
    0.07
    aille
    0.07
    èı
    0.06
    /Internal
    0.06
    åIJģ
    0.06
    UniqueId
    0.06
    viron
    0.06
    åħ¨åĭ¤
    0.06
    è®®ä¼ļ
    0.06
    äch
    0.06
    Activations Density 0.036%

    No Known Activations