© 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. 8033
    Prev
    Next
    INDEX
    Explanations

    generated by

    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
    ãĢħ
    -0.07
    éł
    -0.07
    able
    -0.06
    æľīä¸Ģç§į
    -0.06
    åıijçĶŁè¿ĩ
    -0.06
    æĪIJ为ä¸Ģç§į
    -0.06
    gw
    -0.06
    казÑĭваеÑĤÑģÑı
    -0.06
    ivate
    -0.06
    enders
    -0.06
    POSITIVE LOGITS
    è¿Ļ对
    0.08
    -toggler
    0.08
    ÑĦоÑĢд
    0.07
    hend
    0.07
     appunto
    0.07
    KET
    0.07
    ÑħаÑħ
    0.07
    natur
    0.07
    ettet
    0.07
     intersect
    0.07
    Activations Density 0.087%

    No Known Activations