© 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. 29807
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
    żd
    -0.09
    è®´
    -0.08
    ç±³èĬ±
    -0.08
    trys
    -0.08
    éĽĨåħ¨
    -0.08
    sker
    -0.08
    yte
    -0.08
    åºĶå½ĵä¾Ŀçħ§
    -0.08
    _specs
    -0.08
    DTD
    -0.08
    POSITIVE LOGITS
    reb
    0.06
    ·
    0.06
    è¯Ń
    0.06
    es
    0.06
    los
    0.06
    er
    0.06
    up
    0.06
    awan
    0.06
    æľĿ
    0.06
    utor
    0.06
    Activations Density 0.054%

    No Known Activations