© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29850
    Prev
    Next
    INDEX
    Explanations

    code punctuation or ending punctuation

    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
    upes
    -0.10
     +'
    -0.07
    exception
    -0.07
    éĥijéĩį声æĺİ
    -0.07
    RESS
    -0.07
    è¿Ļåľ¨
    -0.07
    ondes
    -0.06
    .mk
    -0.06
    并ä¸Ķ
    -0.06
     menger
    -0.06
    POSITIVE LOGITS
     Suff
    0.08
    agg
    0.08
    acu
    0.07
    vin
    0.07
     suff
    0.07
    æµ·ä¸Ń
    0.07
    igg
    0.07
    -await
    0.06
    θÎŃ
    0.06
    åIJĦç±»
    0.06
    Activations Density 0.043%

    No Known Activations