© 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. 25365
    Prev
    Next
    INDEX
    Explanations

    flow algorithms

    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
    åİī害çļĦ
    -0.07
    å½Ĵè¿ĺ
    -0.06
    æ¯
    -0.06
    esine
    -0.06
    è¿ĶåĽŀåĪĹ表
    -0.06
     nah
    -0.06
    (Return
    -0.06
    ç¿ĺ
    -0.06
    åİŁæĸĻèį¯
    -0.06
    è¡¥éĴĻ
    -0.06
    POSITIVE LOGITS
    æµģéĩı
    0.11
    flow
    0.10
    æµģéĩıçļĦ
    0.10
     flow
    0.10
     flows
    0.09
    æµģç»ı
    0.09
    -flow
    0.09
     capacities
    0.09
    æµģéĢŁ
    0.09
     capacity
    0.09
    Activations Density 0.005%

    No Known Activations