© 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. 27208
    Prev
    Next
    INDEX
    Explanations

    singleton partition

    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
    rp
    -0.07
    管çĶ¨
    -0.07
    åĤ¨è¿IJ
    -0.07
     Nut
    -0.06
     synthetic
    -0.06
    raw
    -0.06
    åı¯åģļ
    -0.06
     Akron
    -0.06
    Digit
    -0.06
     digit
    -0.06
    POSITIVE LOGITS
    ingleton
    0.09
    ingroup
    0.09
    è¾¹çķĮ
    0.08
     Subset
    0.08
    _subset
    0.08
    _boundary
    0.08
     clearfix
    0.07
    ToF
    0.07
    boundary
    0.07
     minority
    0.07
    Activations Density 0.004%

    No Known Activations