© 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. 45254
    Prev
    Next
    INDEX
    Explanations

    define concept or notion

    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
    shaw
    -0.07
    _heads
    -0.07
    (SIG
    -0.07
    ī´
    -0.07
    ä»ĸä¸įä¼ļ
    -0.06
    SIG
    -0.06
    à¸ģà¸ģ
    -0.06
    μαν
    -0.06
    ä½łä¸įçŁ¥éģĵ
    -0.06
    achel
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹Īåı«
    0.16
    ä»Ģä¹Īæĺ¯
    0.16
     definitions
    0.15
     definition
    0.15
     понÑıÑĤиÑı
    0.14
    å®ļä¹ī
    0.14
    Definition
    0.14
     Definitions
    0.13
     Definition
    0.13
    å®ļä¹īçļĦ
    0.13
    Activations Density 0.151%

    No Known Activations