© 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. 9870
    Prev
    Next
    INDEX
    Explanations

    by

    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
    æĸ°åĬłåĿ¡
    -0.11
    jenigen
    -0.10
    åĬłæĭ¿å¤§
    -0.10
    Ïĥή
    -0.09
    heil
    -0.09
    à¸ģารà¸ĵà¹Į
    -0.09
    ÙĬتÙĬÙĨ
    -0.09
    amente
    -0.09
    ../../../
    -0.08
    ãĤĪãģĨãģ«ãģªãĤĭ
    -0.08
    POSITIVE LOGITS
     virtue
    0.12
    /from
    0.11
    -products
    0.11
    gone
    0.10
    /to
    0.10
    /about
    0.10
     dint
    0.10
    /of
    0.10
    /on
    0.09
     the
    0.09
    Activations Density 0.392%

    No Known Activations