© 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. 30185
    Prev
    Next
    INDEX
    Explanations

    conjunctions or punctuation

    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
    ¾¸
    -0.09
    æĢ§æĺ¯
    -0.08
    пÑĥÑģÑĤ
    -0.07
     furthermore
    -0.07
    ito
    -0.07
    udian
    -0.07
    ikle
    -0.07
    ÑīноÑģÑĤÑĮ
    -0.07
    ä¸įä»ħå¦ĤæѤ
    -0.07
    inski
    -0.07
    POSITIVE LOGITS
    以åıĬ
    0.08
    ।
    0.08
    and
    0.08
    <|box_end|>
    0.08
     **.**
    0.07
    âĢļ
    0.07
    ìĿĺ
    0.07
    çļĦ
    0.07
    otec
    0.06
     and
    0.06
    Activations Density 0.008%

    No Known Activations