© 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. 43094
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems

    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
    ermann
    -0.09
     thÆ°á»Ľc
    -0.09
    ropri
    -0.08
    为äºĨ解åĨ³
    -0.08
    TURE
    -0.08
    ì§Ģê¸Ī
    -0.08
    teenth
    -0.07
    siz
    -0.07
    teg
    -0.07
    ิà¹īà¸ĩ
    -0.07
    POSITIVE LOGITS
    ically
    0.10
    èĪ¬åľ°
    0.08
    ually
    0.08
    ì¹Ļ
    0.08
    家æľī
    0.07
    perature
    0.07
    ickey
    0.07
    althy
    0.07
    èĦ¯
    0.07
    ayer
    0.07
    Activations Density 0.009%

    No Known Activations