© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26926
    Prev
    Next
    INDEX
    Explanations

    maximal subgroups, items, vertices, counting

    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
     ÎŃγι
    -0.08
    awang
    -0.07
    æ¯Ķäºļ
    -0.07
    æĺ¯åIJ¦ä¸İ
    -0.07
    æĺ¯åIJ¦ç¬¦åIJĪ
    -0.07
    .prob
    -0.07
    éĢį
    -0.07
    amm
    -0.07
    alker
    -0.06
    uropa
    -0.06
    POSITIVE LOGITS
    æľĢå¤ļ
    0.11
    èĩ³å°ijè¦ģ
    0.09
    è¦ģéĿł
    0.09
     counted
    0.08
    ä¸įèĥ½è¶ħè¿ĩ
    0.08
    æľĢå¤ļçļĦ
    0.08
    count
    0.08
     maximal
    0.08
     counting
    0.08
    èĩ³å°ij
    0.08
    Activations Density 0.002%

    No Known Activations