© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44709
    Prev
    Next
    INDEX
    Explanations

    Fermi surface and cutoff

    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
    Negative Logits
    æŬ
    -0.08
    _formats
    -0.07
    ppers
    -0.07
    æł¼å¼ıçļĦ
    -0.07
     PROV
    -0.07
     prov
    -0.07
    ÙĤدس
    -0.07
     Indah
    -0.07
    mts
    -0.06
    æķ·
    -0.06
    POSITIVE LOGITS
    utoff
    0.09
     cutoff
    0.09
    æī©å®¹
    0.08
    ä¿ĿæĬ¤æ³ķ
    0.07
    _RADIUS
    0.07
     Unused
    0.07
    _NEED
    0.07
    shell
    0.07
    olume
    0.07
     radius
    0.07
    Activations Density 0.003%

    No Known Activations