© 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. 31224
    Prev
    Next
    INDEX
    Explanations

    problem assignment

    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
    ä¸Ģæĭį
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    åĪ°èĢģ
    -0.07
    ãĥĥãĤ«ãĥ¼
    -0.07
    adel
    -0.07
    μη
    -0.07
    yles
    -0.07
    è¿ĻäºĽè¯Ŀ
    -0.07
    ace
    -0.06
    aler
    -0.06
    POSITIVE LOGITS
    سÙĬ
    0.07
    kopf
    0.07
    åĴĮ第
    0.07
    åĴĮè¦ģæ±Ĥ
    0.07
    UGHT
    0.07
    ulong
    0.07
    allenge
    0.07
    ussin
    0.07
    æĭĸ
    0.07
    åħ¢
    0.07
    Activations Density 0.021%

    No Known Activations