© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17273
    Prev
    Next
    INDEX
    Explanations

    optional, defaults

    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
    cen
    -0.08
    วà¹Īาย
    -0.08
    è¿ĻæŃ£æĺ¯
    -0.07
    lias
    -0.07
    ãģłãĤī
    -0.07
     rév
    -0.07
    .wr
    -0.06
    å¿ĥåľ°
    -0.06
    ffa
    -0.06
    缸åħ³æ³ķå¾ĭ责任
    -0.06
    POSITIVE LOGITS
     optional
    0.10
     negligible
    0.09
    optional
    0.09
     additional
    0.08
    (Optional
    0.08
    åı¯æľī
    0.08
    èĻ«
    0.08
    Optional
    0.08
     defaults
    0.08
    defaults
    0.08
    Activations Density 0.004%

    No Known Activations