© 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. 4451
    Prev
    Next
    INDEX
    Explanations

    problem description or question

    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
    æľīåħ³æĥħåĨµ
    -0.09
    imonial
    -0.08
    使ä¹ĭ
    -0.08
    казÑĭваеÑĤÑģÑı
    -0.08
    çļĦ空éĸĵ
    -0.08
    çļĦéĹľä¿Ĥ
    -0.07
    ÑħодÑĥ
    -0.07
    BuilderFactory
    -0.07
    使å®ĥ
    -0.07
    serter
    -0.07
    POSITIVE LOGITS
    ÅĽc
    0.06
    's
    0.06
    stwo
    0.06
    ve
    0.06
    st
    0.06
     Altern
    0.06
     ÙħسÙĦ
    0.06
     outlined
    0.06
    és
    0.06
    fort
    0.06
    Activations Density 0.001%

    No Known Activations