© 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. 1492
    Prev
    Next
    INDEX
    Explanations

    question marks or placeholders

    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
    <|box_end|>
    -0.12
    peg
    -0.11
    aian
    -0.10
    âĤ¬âĦ¢
    -0.10
    ettle
    -0.10
    ysh
    -0.09
    ...',
    -0.09
    geois
    -0.09
    waran
    -0.09
    ppers
    -0.09
    POSITIVE LOGITS
    s
    0.10
    äºĨ
    0.10
    u
    0.10
    ÙĪ
    0.09
    os
    0.09
    ï¸ı
    0.09
    ar
    0.08
    .
    0.08
    ãĤĪãģĨãģ«
    0.08
    n
    0.08
    Activations Density 0.013%

    No Known Activations