© 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. 61294
    Prev
    Next
    INDEX
    Explanations

    stored or started

    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
    åĪĩæĪIJ
    -0.06
    éĿŀçī©è´¨
    -0.06
     Employment
    -0.06
     méd
    -0.06
     uns
    -0.06
    issi
    -0.06
     emb
    -0.06
     employment
    -0.06
     Grande
    -0.06
     prec
    -0.06
    POSITIVE LOGITS
    ä¸İåīį
    0.15
    æĸ°ãģŁãģ«
    0.11
    æĸ°çļĦ
    0.11
    æĸ°å¢ŀ
    0.10
    æĸ°çļĦä¸Ģ
    0.10
    åīįåĽŀ
    0.10
    (previous
    0.10
     incremental
    0.10
    延ç»ŃäºĨ
    0.10
    æĸ°ãģŁãģª
    0.10
    Activations Density 0.267%

    No Known Activations