© 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. 34067
    Prev
    Next
    INDEX
    Explanations

    prefix:, start time, update yesterday

    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
     (
    -0.07
    åºĶå½ĵæī¿æĭħ
    -0.06
    è¿ĺä¸į
    -0.06
    asp
    -0.06
    ä½Ĩ并ä¸į
    -0.06
     yet
    -0.06
    alone
    -0.06
    acha
    -0.06
    åıĪä¸į
    -0.06
     o
    -0.05
    POSITIVE LOGITS
    ä¹Łç½¢
    0.10
    æĺİæĺİæĺ¯
    0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    0.08
    egin
    0.08
     likewise
    0.08
    缩
    0.08
    ĥĿ
    0.08
    æĤ£
    0.07
    .vx
    0.07
    gris
    0.07
    Activations Density 0.113%

    No Known Activations