© 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. 10902
    Prev
    Next
    INDEX
    Explanations

    numbers and labels

    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
    reck
    -0.07
    -
    -0.06
    "%(
    -0.06
    -0.06
    .
    -0.06
    "
    -0.06
    ot
    -0.06
    (
    -0.05
    ↵
    -0.05
    就已ç»ı
    -0.05
    POSITIVE LOGITS
    bolo
    0.10
    IMAGE
    0.09
    elman
    0.09
    æľ¬æĸĩéĵ¾æİ¥
    0.08
    åħ¬ç½ijå®īå¤ĩ
    0.08
     lév
    0.08
    ÙĬÙĨÙĬØ©
    0.08
    лама
    0.08
    ?,?,?,?,
    0.08
    enie
    0.08
    Activations Density 0.011%

    No Known Activations