© 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. 30838
    Prev
    Next
    INDEX
    Explanations

    dialogs and forms

    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
    Reader
    -0.07
    ä¸Ńåį«
    -0.07
    ×ŀ×ĵ
    -0.07
    Ģ
    -0.06
    æĸĩæijĺ
    -0.06
    ç´¢å¼ķ
    -0.06
     Unterr
    -0.06
    latan
    -0.06
    lát
    -0.06
    Call
    -0.06
    POSITIVE LOGITS
    éĢīæĭ©ä¸Ģ个
    0.09
    请éĢīæĭ©
    0.09
    为ä¸ĸçķĮ
    0.08
    请è¾ĵåħ¥
    0.08
    éĢīæĭ©äºĨ
    0.08
    ä¸Ńè¾ĵåħ¥
    0.08
    çĦ¶åIJİçĤ¹åĩ»
    0.08
    <input
    0.08
    gire
    0.08
    è¿ŀäºij
    0.08
    Activations Density 0.221%

    No Known Activations