© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9288
    Prev
    Next
    INDEX
    Explanations

    lists of aspects and details

    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
    åĬĽè¡Į
    -0.07
    çļĦä¸Ĭ
    -0.07
    å°į象
    -0.07
    instr
    -0.07
    agine
    -0.07
     übrigens
    -0.06
    inize
    -0.06
    atre
    -0.06
     Hass
    -0.06
    info
    -0.06
    POSITIVE LOGITS
    çļĦåĩłä¸ª
    0.07
    æĪijå¿ĥä¸Ń
    0.07
    èŁĨ
    0.07
     fifo
    0.07
     thereof
    0.07
    imon
    0.07
    aho
    0.06
     counter
    0.06
    åĪĨå¤ĸ
    0.06
    è¯Ľ
    0.06
    Activations Density 0.023%

    No Known Activations