© 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. 41103
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    æĹ¶èµ·
    -0.07
    izen
    -0.07
    çļĦæľĭåıĭ们
    -0.07
    isie
    -0.07
    ç§ĺ书
    -0.07
    转载请注æĺİåĩºå¤Ħ
    -0.07
     rezerv
    -0.07
    æĹ¶å¯¹
    -0.07
    .asc
    -0.06
    angelo
    -0.06
    POSITIVE LOGITS
    æįī
    0.08
    tures
    0.07
    oppen
    0.06
    olla
    0.06
    aroo
    0.06
    برÙī
    0.06
    å¾Ĵ
    0.06
    æ¦Ħ
    0.06
    ê³µìĤ¬
    0.06
    ecca
    0.06
    Activations Density 0.001%

    No Known Activations