© 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. 37793
    Prev
    Next
    INDEX
    Explanations

    code snippet

    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
    rieb
    -0.07
    icc
    -0.07
    ieg
    -0.06
    å¼ĢèµĽ
    -0.06
    å°ıçľĭ
    -0.06
    æĵħ
    -0.06
    æİıåĩº
    -0.06
    à¸Ńัà¸Ļ
    -0.06
    ány
    -0.06
    à¸ļาà¸Ļ
    -0.06
    POSITIVE LOGITS
    ahre
    0.08
    ®
    0.07
    ãĤĮãģ®
    0.07
    åįĹçľģ
    0.07
    ifter
    0.07
    istik
    0.07
    ortable
    0.07
    edet
    0.07
    æ±ĩæĢ»è¡¨
    0.07
    天å®ī
    0.07
    Activations Density 0.001%

    No Known Activations