© 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. 25260
    Prev
    Next
    INDEX
    Explanations

    inline device constant

    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
    MOOTH
    -0.08
    wic
    -0.07
    ÑģÑĤв
    -0.07
    lø
    -0.07
    ä¼ĺç§Ģå¥ĸ
    -0.07
    ney
    -0.07
    ropa
    -0.07
    åIJİåį«
    -0.07
    luetooth
    -0.07
    uild
    -0.06
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.08
    åIJijæĹ¥
    0.07
    oland
    0.07
     perspect
    0.07
    otime
    0.07
    aside
    0.07
    è§Ĩè§Ĵ
    0.07
    .pag
    0.06
    èµĦ
    0.06
    -ish
    0.06
    Activations Density 0.002%

    No Known Activations