© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58836
    Prev
    Next
    INDEX
    Explanations

    Isabella, sin, right

    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
     lee
    -0.07
    fatt
    -0.06
    çľ¼çľĭ
    -0.06
    urat
    -0.06
    转
    -0.06
    á»ĩp
    -0.06
    éĶ¤
    -0.06
     Ups
    -0.06
    è¯
    -0.05
    ;
    -0.05
    POSITIVE LOGITS
    راس
    0.08
    èī¯
    0.08
    anson
    0.07
    ä¸ĩä¸Ī
    0.07
    åħ¬èĭ±
    0.07
    áĢĢáĢº
    0.07
    ãĥ«ãĥķ
    0.07
    amins
    0.07
    ä»Ģ
    0.07
    æĺ¨å¤©çļĦ
    0.07
    Activations Density 0.043%

    No Known Activations