© 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. 14483
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and structures

    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
     mene
    -0.08
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.08
    æĮĸæİĺåħ¬åı¸
    -0.08
    [sizeof
    -0.08
    <Input
    -0.08
    ĤŃ
    -0.08
    åĽ½å®¶å¸ĤåľºçĽijçĿ£ç®¡çIJĨæĢ»å±Ģ
    -0.07
    ajat
    -0.07
    ê¹ĥ
    -0.07
    relu
    -0.07
    POSITIVE LOGITS
    æĩ¸
    0.08
    Ĭ
    0.06
    ised
    0.06
     sus
    0.06
    0.06
    Âł
    0.06
    zia
    0.06
    èĢĮå®ļ
    0.06
    SSERT
    0.06
    åħ°çī¹
    0.06
    Activations Density 0.005%

    No Known Activations