© 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. 28698
    Prev
    Next
    INDEX
    Explanations

    prove that

    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
    aight
    -0.10
    çª
    -0.09
    临å®ī
    -0.08
    trup
    -0.08
    _DEPRECATED
    -0.08
    committed
    -0.08
    Scaler
    -0.08
    znak
    -0.08
    轻轻æĿ¾
    -0.08
    tright
    -0.08
    POSITIVE LOGITS
    ı
    0.08
    çĶ±åIJĦ
    0.06
    m
    0.06
    à¸Ńà¸ģ
    0.06
    ccb
    0.06
    0.06
    请å°Ĩ
    0.06
     poup
    0.06
     REUTERS
    0.06
    æ¯Ĺ
    0.06
    Activations Density 0.002%

    No Known Activations