© 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. 37967
    Prev
    Next
    INDEX
    Explanations

    academic/research introductions

    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
    åį´åľ¨
    -0.07
    agnol
    -0.07
     justru
    -0.07
    æľīçĿĢ
    -0.06
    èĦ
    -0.06
    ç½ķ
    -0.06
    éľĸ
    -0.06
    é¼
    -0.06
    anders
    -0.06
    onomy
    -0.06
    POSITIVE LOGITS
    ICH
    0.07
    çļĦ认è¯Ĩ
    0.07
    丸
    0.07
    orman
    0.06
    emoth
    0.06
     systemic
    0.06
    tii
    0.06
    à¸į
    0.06
    enni
    0.06
    çİĦ
    0.06
    Activations Density 0.018%

    No Known Activations