© 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. 49836
    Prev
    Next
    INDEX
    Explanations

    method, based on, approach, mining

    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
    ½ij
    -0.08
    lined
    -0.08
    èij
    -0.07
    agam
    -0.07
    mez
    -0.07
    ynes
    -0.07
    ãĤ¹ãĤ±
    -0.07
    elaar
    -0.07
    lease
    -0.07
    åĿª
    -0.07
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹æ³ķ
    0.15
     approach
    0.13
    -based
    0.13
    è¿Ļ个æĸ¹æ³ķ
    0.12
    ãĤ¢ãĥĹãĥŃãĥ¼ãĥģ
    0.11
    -Based
    0.11
    å¼ı
    0.11
     Approach
    0.11
    æ³ķ
    0.10
    æ³ķçļĦ
    0.10
    Activations Density 0.347%

    No Known Activations