© 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. 12962
    Prev
    Next
    INDEX
    Explanations

    æąˇæľī google

    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
    ами
    -0.11
    uous
    -0.10
    occas
    -0.10
    å¾Ĺèµ·
    -0.10
    çĿĢä¸ĢèĤ¡
    -0.09
    ä¸ĢæľĿ
    -0.09
    çļĦåıĮéĩį
    -0.09
    ìĿĺ
    -0.09
    ually
    -0.09
    äºİä¸Ģ身
    -0.09
    POSITIVE LOGITS
    äºĨä¸ĢåĪĩ
    0.09
    äºĨä¸ĢäºĽ
    0.08
    ä¾ĨçļĦ
    0.08
    thers
    0.08
    äºĨä¸Ģ
    0.08
    çļĦæĺ¯ä¸Ģ个
    0.08
    thing
    0.07
    gether
    0.07
    äºĨä¸ĢèĪ¬
    0.07
    èĩªå·±çļĦ
    0.07
    Activations Density 0.002%

    No Known Activations