© 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. 22652
    Prev
    Next
    INDEX
    Explanations

    white light, between the

    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
    azza
    -0.07
     Early
    -0.06
    åIJĦç§įåİŁåĽł
    -0.06
    adol
    -0.06
    æł¹æį®
    -0.06
     Pax
    -0.06
     früh
    -0.06
    æijĩ
    -0.06
    ÑĪÑĤÑĥ
    -0.06
    SEQ
    -0.06
    POSITIVE LOGITS
    ä¹ĭæīĢ以
    0.09
    ]]=
    0.08
    +offset
    0.08
    onium
    0.08
    arest
    0.08
    åķıé¡Įãģ¯
    0.08
    çł´
    0.07
    yip
    0.07
    好ä¸į好
    0.07
    åľ°åĿĢä½įäºİ
    0.07
    Activations Density 0.235%

    No Known Activations