© 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. 40294
    Prev
    Next
    INDEX
    Explanations

    concavity

    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
    ä¸įåı¯æĢķ
    -0.08
    amanya
    -0.08
    agra
    -0.07
    ä¿ĬæĿ°
    -0.07
    idin
    -0.07
    æµģæ°ĵ
    -0.07
    UDI
    -0.07
    orr
    -0.07
    éķ¿åģĩ
    -0.07
    azo
    -0.07
    POSITIVE LOGITS
    irk
    0.10
     Jensen
    0.09
    anko
    0.08
     convex
    0.08
    ogue
    0.08
    åĩ¹
    0.07
    å¹³åĿĩåĢ¼
    0.07
    åĩ¹éĻ·
    0.07
    ensen
    0.07
     midpoint
    0.07
    Activations Density 0.002%

    No Known Activations