© 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. 10269
    Prev
    Next
    INDEX
    Explanations

    either word or track listing

    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
    idd
    -0.07
    éļ¾å¾Ĺ
    -0.07
    ww
    -0.07
    abda
    -0.06
    çī¹æ®Ĭ
    -0.06
    ÑĪаÑĤ
    -0.06
     outings
    -0.06
    onha
    -0.06
    ogr
    -0.06
    resh
    -0.06
    POSITIVE LOGITS
    æľī两ç§į
    0.22
     either
    0.21
    either
    0.21
     Ø¥Ùħا
    0.18
    Either
    0.18
    两ç§įæĸ¹å¼ı
    0.18
    两ç§į
    0.18
     Either
    0.17
     EITHER
    0.17
    è¦ģä¹Ī
    0.17
    Activations Density 0.597%

    No Known Activations