© 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. 63979
    Prev
    Next
    INDEX
    Explanations

    scientific article titles

    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
    s
    -0.09
    </think>
    -0.08
    n
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    ÙĪÙħØ©
    -0.07
    uint
    -0.07
    imes
    -0.07
    j
    -0.07
    ting
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    POSITIVE LOGITS
    edException
    0.09
    ä½Ĩæĺ¯å®ĥ
    0.09
    ####
    0.08
    ihi
    0.08
    аб
    0.08
    eper
    0.08
    '](
    0.08
    ###
    0.08
    sis
    0.08
    pector
    0.08
    Activations Density 0.008%

    No Known Activations