© 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. 22521
    Prev
    Next
    INDEX
    Explanations

    units digit

    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
    cius
    -0.09
    Å¡nÃŃ
    -0.08
    chantment
    -0.08
    åħ·æľīå¾Ī
    -0.08
    AVING
    -0.08
    åĵĪèIJ¨
    -0.08
    stown
    -0.08
    ä½Ļå¹´
    -0.08
    è½°è½°
    -0.08
    Sizes
    -0.08
    POSITIVE LOGITS
    篱
    0.06
    æĹ¥æĻļ
    0.06
    æĹ©
    0.06
     n
    0.06
    night
    0.06
    èĤĺ
    0.06
    åĴĮçĻ½
    0.05
    åĽŀé¦ĸ
    0.05
    /k
    0.05
    —an
    0.05
    Activations Density 0.287%

    No Known Activations