© 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. 26538
    Prev
    Next
    INDEX
    Explanations

    inhibin, Kivu, Mother, bottom panel, auto-scale up

    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
    çĶŁä¸ĭ
    -0.07
    erged
    -0.07
    ÏĢή
    -0.07
    _>
    -0.07
    anners
    -0.07
    Broken
    -0.07
    _NB
    -0.07
    iten
    -0.07
    ppen
    -0.07
    posal
    -0.07
    POSITIVE LOGITS
    æĪIJ家
    0.07
    磷
    0.07
    hre
    0.07
    /
    0.07
    ãĢģ
    0.07
    è´µ
    0.07
    åĶ¯
    0.07
    imation
    0.07
    inde
    0.06
     and
    0.06
    Activations Density 0.187%

    No Known Activations