© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    function outputs and mappings

    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
    iom
    -0.08
    _finalize
    -0.07
    书åIJ§
    -0.07
    ê·ł
    -0.07
    gai
    -0.07
     tunt
    -0.07
     pneumat
    -0.07
    ulg
    -0.07
    éļħ
    -0.07
    ÄĹt
    -0.07
    POSITIVE LOGITS
    æĺłå°Ħ
    0.08
     assigns
    0.07
    æĬ½
    0.07
     mappings
    0.07
    Arrow
    0.07
    èIJ½æ°´
    0.07
    Outputs
    0.07
     mapping
    0.07
    ÙĪÙĨÙĩ
    0.07
    istrict
    0.07
    Activations Density 0.010%

    No Known Activations