© 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. 44162
    Prev
    Next
    INDEX
    Explanations

    filenames containing years

    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
    微信æī«çłģ
    -0.08
    ryptography
    -0.08
     okaz
    -0.07
    ιÏĥÏĦα
    -0.07
    æķħæѤ
    -0.07
    stellungen
    -0.07
     Vat
    -0.07
    جازات
    -0.07
    eret
    -0.07
    дии
    -0.07
    POSITIVE LOGITS
     canon
    0.06
    reen
    0.06
     hard
    0.06
    ogr
    0.06
    t
    0.06
     assumed
    0.06
    bel
    0.06
     cold
    0.06
    æ¯Ķèĩªå·±
    0.06
    FW
    0.06
    Activations Density 0.046%

    No Known Activations