© 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. 16954
    Prev
    Next
    INDEX
    Explanations

    to turn off/not sure/might have

    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
    å®ĥæīĢ
    -0.08
    æĪIJåĬŁåľ°
    -0.07
    whatever
    -0.07
    åľ¨å®ĥ
    -0.07
    对å®ĥ
    -0.07
    以åıĬåIJĦç§į
    -0.07
    羣æŃ£åľ°
    -0.07
    æ·±åĪ»åľ°
    -0.07
    ,
    -0.07
    æ·±æ·±åľ°
    -0.07
    POSITIVE LOGITS
    ×Ļרת
    0.09
     chÄĥng
    0.08
    注æĦıçļĦæĺ¯
    0.08
    æľ¬äºº
    0.08
    çļĦè¿ĺæľī
    0.08
    dda
    0.08
    ÂŃing
    0.08
    éľĢ
    0.07
    åIJĮä¸Ĭ
    0.07
    çļĦæĪij
    0.07
    Activations Density 0.125%

    No Known Activations