© 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. 57455
    Prev
    Next
    INDEX
    Explanations

    in line

    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
    2
    -0.07
    -
    -0.06
    anson
    -0.06
    (
    -0.06
    æı
    -0.06
    agers
    -0.05
    agg
    -0.05
    o
    -0.05
    èĦ±ä¸ĭ
    -0.05
    EMS
    -0.05
    POSITIVE LOGITS
    æĪijè¦ģæĬķè¯ī
    0.09
    åĭ¤åĭ¤æģ³æģ³
    0.09
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    stime
    0.09
    èĢ³çĨŁèĥ½è¯¦
    0.08
    .school
    0.08
    两åѦä¸Ģåģļ
    0.08
    etag
    0.08
    è®©æĽ´å¤ļ读èĢħ
    0.08
    åIJĦç§įåIJĦæł·
    0.08
    Activations Density 0.001%

    No Known Activations