© 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. 19853
    Prev
    Next
    INDEX
    Explanations

    appearance, form, dimensions, information

    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
    çĮ®çŃĸ
    -0.08
    anita
    -0.08
    pliers
    -0.08
     Hamm
    -0.08
    åħ¸åŀĭ
    -0.08
    edImage
    -0.07
    æķĪçİĩé«ĺ
    -0.07
    äºĶ人
    -0.07
    çĻ¾äºº
    -0.07
    -Ta
    -0.07
    POSITIVE LOGITS
    æ·±æµħ
    0.09
     aspect
    0.09
     aspects
    0.08
    åı¯è¨Ģ
    0.08
     complexion
    0.08
    ç²Ĺç»Ĩ
    0.08
    çļĦé«ĺä½İ
    0.07
    åĨ³å®ļçļĦ
    0.07
    ä¸ī个æĸ¹éĿ¢
    0.07
    äºĭçī©çļĦ
    0.07
    Activations Density 0.070%

    No Known Activations