© 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. 21242
    Prev
    Next
    INDEX
    Explanations

    interest and growth

    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
    æī£åĪĨ
    -0.08
    è£ģåīª
    -0.08
     spectra
    -0.08
    Õ»
    -0.08
    è£ģ
    -0.08
    ç¶ĵè²»
    -0.08
    åĩıåİĭ
    -0.08
    arach
    -0.08
    ì¶Ķ
    -0.08
    伶
    -0.07
    POSITIVE LOGITS
    æģ¯
    0.09
     deposit
    0.08
     compounded
    0.08
     Depos
    0.08
     accrued
    0.08
    åŃĺåħ¥
    0.08
     deposited
    0.08
    计ç®ĹåĻ¨
    0.08
     growth
    0.08
    éĵ¶è¡Į
    0.08
    Activations Density 0.025%

    No Known Activations