© 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. 62670
    Prev
    Next
    INDEX
    Explanations

    numeric and alphanumeric sequences

    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
    byn
    -0.08
    bedo
    -0.08
    lector
    -0.08
    yota
    -0.08
    quam
    -0.08
    volv
    -0.08
    oped
    -0.08
    pong
    -0.08
    ยà¸Ńà¸Ķ
    -0.08
    ×ŀ×ķ
    -0.08
    POSITIVE LOGITS
    stone
    0.08
    atin
    0.07
    ï¸ı
    0.07
    inge
    0.06
    res
    0.06
    ly
    0.06
    thon
    0.06
    æ¡IJ乡
    0.06
    èģĶè°Ĭä¼ļ
    0.06
    aton
    0.06
    Activations Density 0.037%

    No Known Activations