© 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. 34445
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

    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
    _globals
    -0.09
    AGMA
    -0.09
    evin
    -0.09
    amba
    -0.09
    ugins
    -0.09
    alami
    -0.08
    åıĬ以ä¸ĬçļĦ
    -0.08
    aturi
    -0.08
     definitiv
    -0.08
    opa
    -0.08
    POSITIVE LOGITS
     etc
    0.08
    说ä¸įå®ļ
    0.07
    [
    0.07
    ite
    0.06
    in
    0.06
    (
    0.06
     in
    0.06
    ä¹ĭç±»çļĦ
    0.06
    /
    0.06
     certain
    0.06
    Activations Density 0.017%

    No Known Activations