© 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. 3052
    Prev
    Next
    INDEX
    Explanations

    pour liquid into

    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
    人士
    -0.08
    ض
    -0.08
    åģļçļĦå°±æĺ¯
    -0.08
    å¼ĤçļĦ
    -0.08
    ope
    -0.08
    ÙĬÙģØ©
    -0.08
    espace
    -0.08
    ynos
    -0.08
    .twitter
    -0.07
    Äįaj
    -0.07
    POSITIVE LOGITS
     onto
    0.10
    Into
    0.08
    ä¸Ģ空
    0.08
     ulang
    0.08
    æ´Ĵ
    0.08
    ä¸ĭåİ»
    0.08
    ä¸Ģæ»´
    0.08
    æ·ĭæ¼ĵ
    0.08
     into
    0.08
    _into
    0.08
    Activations Density 0.028%

    No Known Activations