© 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. 49459
    Prev
    Next
    INDEX
    Explanations

    legal or organizational groups

    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
    ãģ³
    -0.07
     lek
    -0.07
     Bens
    -0.07
     Pen
    -0.06
    acos
    -0.06
     Simmons
    -0.06
    ä¸įè§ĦèĮĥ
    -0.06
    InstanceOf
    -0.06
    å¦Ĥ约
    -0.06
    .lex
    -0.06
    POSITIVE LOGITS
     grouping
    0.17
    ä¸Ģç»Ħ
    0.16
    -group
    0.14
     group
    0.14
    ç»Ħ
    0.14
    çļĦä¸Ģç»Ħ
    0.13
    éĽĨ群
    0.13
    ç»ĦçļĦ
    0.13
     grouped
    0.13
     cluster
    0.13
    Activations Density 0.568%

    No Known Activations