© 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. 9324
    Prev
    Next
    INDEX
    Explanations

    indeed or actually

    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
    iskan
    -0.08
    Ñģел
    -0.08
    俱ä¹IJéĥ¨
    -0.07
    apé
    -0.07
    幸è¿IJçļĦæĺ¯
    -0.07
    æĤī
    -0.07
    Ñĥне
    -0.07
    utel
    -0.07
    .Mutable
    -0.07
    榴
    -0.07
    POSITIVE LOGITS
    確ãģĭãģ«
    0.13
     indeed
    0.12
    æĢİä¹Īåı¯èĥ½
    0.12
    æĺİæĺİæĺ¯
    0.11
    ç¡®å®ŀ
    0.11
    羣çļĦæĺ¯
    0.11
    æĢİä¹Īä¼ļ
    0.10
    Indeed
    0.10
    ç¡®å®ŀæĺ¯
    0.10
     actually
    0.10
    Activations Density 0.078%

    No Known Activations