© 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. 33046
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or specific words

    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
    áy
    -0.09
    è¸ıè¸ıå®ŀ
    -0.07
    mato
    -0.07
    glich
    -0.07
    IZA
    -0.07
    æѤæ¡Ī
    -0.07
    izm
    -0.07
     fov
    -0.07
    è®¤è®¤çľŁçľŁ
    -0.07
    åįĥ
    -0.07
    POSITIVE LOGITS
    ãĢģ“
    0.08
    rist
    0.07
    aeda
    0.07
    \.
    0.07
    terior
    0.07
    aat
    0.06
    æİ¥çĿĢ
    0.06
    ãĢģãĢİ
    0.06
    亦çĦ¶
    0.06
     ----------------------------------------------------------------------------------------------------------------
    0.06
    Activations Density 0.031%

    No Known Activations