© 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. 22086
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    sher
    -0.08
    icker
    -0.08
    ]|[
    -0.07
    ÐľÐ£
    -0.07
    ÅĻ
    -0.07
    éģĩ
    -0.07
    ÂŃs
    -0.07
    _assoc
    -0.07
    ersh
    -0.06
    _associ
    -0.06
    POSITIVE LOGITS
    qui
    0.08
    家家
    0.07
    ground
    0.07
    åľ¨åľ°ä¸Ĭ
    0.07
    sic
    0.06
    lik
    0.06
    STATIC
    0.06
    åIJijæĤ¨
    0.06
    forth
    0.06
    ptime
    0.06
    Activations Density 0.233%

    No Known Activations