© 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. 26046
    Prev
    Next
    INDEX
    Explanations

    girl's room class litre cups

    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
    æł¼æĸ¯
    -0.07
    åłĤåłĤ
    -0.07
    iffs
    -0.07
    igma
    -0.07
    大è§Ħ模
    -0.06
     Dezembro
    -0.06
    ä¸īè§Ĥ
    -0.06
     Goldberg
    -0.06
    etus
    -0.06
    adle
    -0.06
    POSITIVE LOGITS
    ostal
    0.09
    åįłæĢ»
    0.09
     оÑģÑĤ
    0.08
    éģĵéķ¿
    0.08
    æĸ°æ°ij
    0.08
    estin
    0.08
    æ¯Ķåݻ年åIJĮæľŁ
    0.07
     sourceMapping
    0.07
    hos
    0.07
    åݻ年çļĦ
    0.07
    Activations Density 0.034%

    No Known Activations