© 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. 19403
    Prev
    Next
    INDEX
    Explanations

    narnia, elder scrolls, counsel

    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
    RW
    -0.07
    åľ¨å®ħ
    -0.06
    ;
    -0.06
    å¼ĢåĬ¨
    -0.06
    è½»æĿ¾åľ°
    -0.06
    é£ŀåİ»
    -0.06
     adjud
    -0.06
    vek
    -0.06
    ä¸ĸ家
    -0.06
    umba
    -0.06
    POSITIVE LOGITS
    ye
    0.09
    ayah
    0.08
    веÑĢ
    0.08
    jab
    0.08
    west
    0.08
    æĺ¨å¤©çļĦ
    0.08
    活水
    0.08
    <|box_end|>
    0.08
    àµįà´¯
    0.07
    _lens
    0.07
    Activations Density 0.006%

    No Known Activations