© 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. 55492
    Prev
    Next
    INDEX
    Explanations

    rights reserved. // license

    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
    .alpha
    -0.08
    reden
    -0.07
    avascript
    -0.07
    ÄĻg
    -0.07
    æĹ¢å®ļ
    -0.07
    cast
    -0.07
    faits
    -0.07
    æ¸ī
    -0.07
    é»į
    -0.07
    SOURCE
    -0.07
    POSITIVE LOGITS
    KK
    0.08
    æ½¢
    0.07
    æĮĸæİĺåħ¬åı¸
    0.07
     cul
    0.07
    éĽį
    0.07
     beware
    0.07
    å¤ĸåħ¬
    0.06
    <|box_end|>
    0.06
    æī¾æĪ¿
    0.06
    IMS
    0.06
    Activations Density 0.001%

    No Known Activations