© 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. 13266
    Prev
    Next
    INDEX
    Explanations

    comparing frequency thresholds

    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
    sWith
    -0.13
    lessness
    -0.09
    lessly
    -0.09
    erman
    -0.09
    skr
    -0.09
    翼翼
    -0.09
    åŃIJéĩĮ
    -0.08
    stead
    -0.08
    swith
    -0.08
    eras
    -0.08
    POSITIVE LOGITS
    “
    0.09
    gether
    0.09
    Ùĩ
    0.08
    åIJĦç§įåİŁåĽł
    0.08
    æŁIJç§į
    0.08
    åIJĦç§į
    0.07
    èģĮå®Ī
    0.07
    htub
    0.07
    ÅĽmy
    0.07
    人æĦı
    0.07
    Activations Density 0.001%

    No Known Activations