© 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. 31923
    Prev
    Next
    INDEX
    Explanations

    computational research and programming

    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
    loff
    -0.07
    æĪ
    -0.07
    erta
    -0.07
    ikers
    -0.07
    éħ
    -0.06
    èĭ¥ä¸įæĺ¯
    -0.06
    没æľīåĩºçİ°
    -0.06
    æº
    -0.06
    ropri
    -0.06
    /mat
    -0.06
    POSITIVE LOGITS
    enums
    0.07
    åĪĨæŀIJä¸Ģä¸ĭ
    0.07
    å¤ķéĺ³
    0.07
    ä¼ij
    0.07
    éĢłåĮĸ
    0.07
    å°½æĺ¯
    0.06
     Arm
    0.06
     Bennett
    0.06
    apes
    0.06
    æĻ¨æĽ¦
    0.06
    Activations Density 0.006%

    No Known Activations