© 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. 19385
    Prev
    Next
    INDEX
    Explanations

    can calculate, create, assume, recognize

    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
    以å¢ŀåĬł
    -0.07
    è¿Ļä¹Īç®Ģåįķ
    -0.07
    enges
    -0.07
    以éĻįä½İ
    -0.07
    æĢ§æĪĸ
    -0.07
     ÙĪاج
    -0.07
     lieber
    -0.07
    以æıIJé«ĺ
    -0.07
     copia
    -0.07
    ë´ħëĭĪëĭ¤
    -0.07
    POSITIVE LOGITS
     easily
    0.10
    å¾Ī容æĺĵ
    0.09
     facilmente
    0.09
     facilement
    0.08
     fácilmente
    0.08
     quickly
    0.08
    å°±å¾Ī容æĺĵ
    0.07
     confidently
    0.07
    å¾Īå¿«çļĦ
    0.07
     hopefully
    0.07
    Activations Density 0.028%

    No Known Activations