© 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. 45159
    Prev
    Next
    INDEX
    Explanations

    code comments and delimiters

    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
    çŃł
    -0.07
    è¿Ļ两个
    -0.06
    ½
    -0.06
    æĺ¯ä¸¤ä¸ª
    -0.06
    ivu
    -0.05
    or
    -0.05
    orenzo
    -0.05
    ren
    -0.05
    éĹ·
    -0.05
    otan
    -0.05
    POSITIVE LOGITS
    линд
    0.08
    ä½ľåĪĻ
    0.08
     lév
    0.08
    çľĭå®ĮäºĨ
    0.08
    åºĶçĶ¨æĬĢæľ¯
    0.08
    èĥ½åĬĽåıĬ
    0.08
    ÄĻd
    0.07
    elh
    0.07
     bills
    0.07
    daq
    0.07
    Activations Density 0.005%

    No Known Activations