© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8917
    Prev
    Next
    INDEX
    Explanations

    character č followed by comma

    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
    «
    -0.08
    stitu
    -0.07
    .escape
    -0.07
    ackt
    -0.07
    ä¹ĭ以
    -0.07
    ãģŃ
    -0.07
    reatest
    -0.07
    versa
    -0.07
    indr
    -0.07
    ÙĪار
    -0.06
    POSITIVE LOGITS
    æ³ķå¾ĭä¿ĿæĬ¤
    0.07
    ;set
    0.07
    %A
    0.06
    zuk
    0.06
    áo
    0.06
    çijľ
    0.06
    åIJĵ人
    0.06
    åĪ°æĤ¨
    0.06
     ranges
    0.06
    çļĦä¿ĿæĬ¤
    0.06
    Activations Density 0.303%

    No Known Activations