© 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. 830
    Prev
    Next
    INDEX
    Explanations

    part, closed, date, author

    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
    次
    -0.07
    ì¡´
    -0.07
    ana
    -0.06
    åĪĩ
    -0.06
    éĵĥ
    -0.06
     Tough
    -0.06
    acle
    -0.06
    ׳×Ķ
    -0.06
    ilar
    -0.06
    ä¸Ĭè¿Ľ
    -0.06
    POSITIVE LOGITS
    çļĦä¸ĵæłı
    0.08
    åħĪåıij
    0.08
    tras
    0.07
    ä»»åħį
    0.07
    ãĥ¼ãĤ¸ãĤ§ãĥ³ãĥĪ
    0.07
    ÙĥÙĬÙħ
    0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    0.07
    ATURAN
    0.07
    ags
    0.07
    buk
    0.07
    Activations Density 0.001%

    No Known Activations