© 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. 20551
    Prev
    Next
    INDEX
    Explanations

    column names or row names

    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
    pong
    -0.08
    æijĬ
    -0.08
    æĢ»ä½ĵ
    -0.07
    γη
    -0.07
    imana
    -0.07
     hÃłng
    -0.07
    regs
    -0.07
    elry
    -0.07
    ä¸īéĥ¨æĽ²
    -0.07
    æĢ»éĩı
    -0.07
    POSITIVE LOGITS
     names
    0.10
     labels
    0.09
    labels
    0.09
    names
    0.09
     identifiers
    0.09
    enames
    0.08
     format
    0.08
    .names
    0.08
     naming
    0.07
     alphabetical
    0.07
    Activations Density 0.158%

    No Known Activations