© 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. 56924
    Prev
    Next
    INDEX
    Explanations

    powers and fractions

    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
    alah
    -0.06
    hk
    -0.06
    oce
    -0.06
    æĢĢåŃķäºĨ
    -0.06
    hq
    -0.06
    elus
    -0.06
    çļĦé«ĺ度
    -0.06
    icile
    -0.06
    å±±ãģ®
    -0.06
    æľīç»Ħç»ĩ
    -0.06
    POSITIVE LOGITS
    iché
    0.07
    crest
    0.07
    éŃĦ
    0.07
    åĽŀäºĭ
    0.07
    rvine
    0.07
    à¤ĺ
    0.07
    ä¸ĢåĽŀäºĭ
    0.07
    зÑĢа
    0.07
    ¢
    0.07
    ferred
    0.07
    Activations Density 0.008%

    No Known Activations