© 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. 50168
    Prev
    Next
    INDEX
    Explanations

    my [technical/personal context]

    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
    ters
    -0.06
    ä¸ĭ表
    -0.06
    еÑĤÑĮ
    -0.06
     disputed
    -0.06
    wis
    -0.06
    atic
    -0.06
    认
    -0.06
    éĤ£æĺ¯ä¸Ģ个
    -0.06
    çį
    -0.06
    sche
    -0.06
    POSITIVE LOGITS
    chand
    0.08
    åIJĽå®ī
    0.08
     tod
    0.08
    atil
    0.08
    .bt
    0.08
    çļĦæŶåĢĻäºĨ
    0.07
    иÑĤелÑĮÑģÑĤво
    0.07
    obo
    0.07
    æĸ°è¦ģæ±Ĥ
    0.07
    bieter
    0.07
    Activations Density 0.005%

    No Known Activations