© 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. 56591
    Prev
    Next
    INDEX
    Explanations

    entity/entities or creature

    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
    缸è¾ħ缸æĪIJ
    -0.09
    ä¸įåı¯æĢĿè®®
    -0.08
    пÑĢода
    -0.08
    cro
    -0.07
    ills
    -0.07
    kl
    -0.07
    oubl
    -0.07
    wards
    -0.07
    पà¥ĭ
    -0.07
    价为
    -0.07
    POSITIVE LOGITS
    wechsel
    0.09
    ##_
    0.09
    ement
    0.09
     called
    0.08
    à¤Ĺत
    0.08
    åĦ¿çļĦ
    0.08
    hood
    0.08
     whose
    0.08
    åIJįåı«
    0.08
    ëĵ¤ìĿĺ
    0.08
    Activations Density 0.503%

    No Known Activations