© 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. 15378
    Prev
    Next
    INDEX
    Explanations

    early in texts

    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
    ifa
    -0.07
    riz
    -0.07
    +$
    -0.07
    oure
    -0.07
    owo
    -0.07
    ilton
    -0.07
    IFA
    -0.07
     Bár
    -0.07
    osa
    -0.06
     REGARD
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.09
    ignite
    0.07
     <![
    0.07
    åĬłæĭ¿å¤§
    0.06
    éĥİ
    0.06
    usc
    0.06
    çł´å¤©
    0.06
    åIJįåī¯
    0.06
     تÙĤرÙĬب
    0.06
    ä¸įå®ĮçļĦ
    0.06
    Activations Density 0.006%

    No Known Activations