© 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. 11381
    Prev
    Next
    INDEX
    Explanations

    introducing subjects or topics

    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
    º
    -0.10
    ly
    -0.08
    羣æĬĵ
    -0.08
    à¸Ńยà¹Īาà¸ĩยิà¹Īà¸ĩ
    -0.08
    sic
    -0.08
    .vn
    -0.07
    ä¹ĭ为
    -0.07
     ($_
    -0.07
     ($(
    -0.07
    å¾Ĺèµ·
    -0.07
    POSITIVE LOGITS
     described
    0.07
    chg
    0.06
     concerned
    0.06
     that
    0.06
    ppy
    0.06
    带好
    0.06
    Speak
    0.06
     discussed
    0.06
     specified
    0.06
    åħ¬åħ±é¢Ħç®Ĺ
    0.06
    Activations Density 0.432%

    No Known Activations