© 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. 51237
    Prev
    Next
    INDEX
    Explanations

    volume, area, proportion

    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
    åįĹé£İ
    -0.08
    istar
    -0.07
    _stderr
    -0.07
    å°Ħç¨ĭ
    -0.07
    ä¸ŃéĢĶ
    -0.06
    uman
    -0.06
    wehr
    -0.06
    溯æºIJ
    -0.06
    iri
    -0.06
     sour
    -0.06
    POSITIVE LOGITS
    åįł
    0.12
    åįłæ¯Ķ
    0.12
    æīĢåįł
    0.12
     fraction
    0.12
    åįłæľīçİĩ
    0.11
     chiếm
    0.11
    空éļĻ
    0.11
     occupies
    0.11
    è¦ĨçĽĸçİĩ
    0.11
     occupied
    0.11
    Activations Density 0.044%

    No Known Activations