© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29756
    Prev
    Next
    INDEX
    Explanations

    geometric and proof-related concepts

    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
    oroz
    -0.08
    åİŁåĪĻä¸Ĭ
    -0.08
    ä¸ĬéĻIJ
    -0.07
    ä¸ĭéĻIJ
    -0.07
     Fits
    -0.07
    ollo
    -0.07
    åįķæĹ¥
    -0.07
    IDL
    -0.07
    åįķä½įåĴĮ个人
    -0.07
    erk
    -0.07
    POSITIVE LOGITS
    åĩłä½ķ
    0.09
     congr
    0.09
     geometric
    0.08
    é£İçŃĿ
    0.08
    åĪĿäºĮ
    0.08
    equality
    0.08
     trig
    0.08
     distances
    0.08
     relational
    0.08
    è¯ģæĺİäºĨ
    0.08
    Activations Density 0.005%

    No Known Activations