© 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. 3500
    Prev
    Next
    INDEX
    Explanations

    .css text

    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
     Auss
    -0.06
    anson
    -0.06
    å¥ĭæĸĹçļĦ
    -0.06
    erna
    -0.05
    ITCH
    -0.05
    ails
    -0.05
    åħ³æľº
    -0.05
    åľ¨åĪ«äºº
    -0.05
    zana
    -0.05
    计ç®ĹåĻ¨
    -0.05
    POSITIVE LOGITS
    atr
    0.07
    æĪijçŃī
    0.07
    oho
    0.07
    éĥ½æľīåı¯èĥ½
    0.07
     berb
    0.07
    ç»İ
    0.07
    ||||
    0.07
    ÙĥرÙĪÙĨ
    0.07
    halt
    0.07
    -kit
    0.07
    Activations Density 0.002%

    No Known Activations