© 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. 19509
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ¯
    -0.06
    bjerg
    -0.06
    íı¬
    -0.06
    ubile
    -0.06
    âĦĸ
    -0.06
    odia
    -0.06
    سÙĪب
    -0.05
    ('{
    -0.05
    FO
    -0.05
    éĩĮåħĭ
    -0.05
    POSITIVE LOGITS
    ÙĦاÙģ
    0.08
    USTA
    0.08
    assel
    0.08
    jede
    0.08
    RowCount
    0.07
    ersp
    0.07
    ä¸įèĩª
    0.07
    满èĦ¸
    0.07
    ACKET
    0.07
    Ø®ÙĨ
    0.07
    Activations Density 0.018%

    No Known Activations