© 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. 56996
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    à¹ģà¸Ħ
    -0.07
    .Cache
    -0.07
    plet
    -0.06
    éĺ´
    -0.06
    eron
    -0.06
    erts
    -0.06
    بÛĮ
    -0.06
    assi
    -0.06
    족
    -0.06
    解ç¦ģ
    -0.06
    POSITIVE LOGITS
    edio
    0.09
    ÄĻcz
    0.09
    undial
    0.08
    æ±²
    0.08
    uris
    0.08
    ÙĩØ©
    0.07
    -font
    0.07
    idth
    0.07
    ritis
    0.07
    uppe
    0.07
    Activations Density 0.003%

    No Known Activations