© 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. 14882
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    åħľ
    -0.08
    ecie
    -0.08
    ç»´æĸ¯
    -0.07
    oyer
    -0.07
     Lover
    -0.07
    奥æķ°
    -0.07
    åĨįåģļ
    -0.06
    ä¸Ģ空
    -0.06
    γμα
    -0.06
    uggy
    -0.06
    POSITIVE LOGITS
    alten
    0.08
    _UNDEFINED
    0.07
     Levine
    0.07
    keley
    0.06
    .fs
    0.06
    oire
    0.06
    ubl
    0.06
     Bale
    0.06
    ä¸ĭæĸĩ
    0.06
    æģĴå¿ĥ
    0.06
    Activations Density 0.176%

    No Known Activations