© 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. 26054
    Prev
    Next
    INDEX
    Explanations

    example config NOTE

    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
    AUSE
    -0.09
    ARSE
    -0.08
    ibold
    -0.08
    enam
    -0.08
    Fld
    -0.08
    arius
    -0.08
    ÙĪرÙĬ
    -0.08
    λι
    -0.08
    িনি
    -0.08
    羯
    -0.08
    POSITIVE LOGITS
    io
    0.07
    å²±
    0.07
    est
    0.06
    æĺĩ
    0.06
    æķ´
    0.06
    кеÑĤ
    0.06
    iet
    0.06
     contr
    0.06
    æĥħåĨµåĪĨæŀIJ
    0.06
    h
    0.06
    Activations Density 0.164%

    No Known Activations