© 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. 47061
    Prev
    Next
    INDEX
    Explanations

    cylinder or cylindrical shapes

    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
     vặt
    -0.08
    oin
    -0.08
    mals
    -0.08
    yer
    -0.07
     ÙĦÙĦغاÙĬØ©
    -0.07
    สุà¸Ķยà¸Ńà¸Ķ
    -0.07
    è¿Ļæĺ¯ä¸Ģ
    -0.07
    fulness
    -0.07
    à¸Ńยà¹Īาà¸ĩยิà¹Īà¸ĩ
    -0.07
    ubl
    -0.07
    POSITIVE LOGITS
    ÑĩаÑĤ
    0.10
    indrical
    0.10
    ë§ģ
    0.08
    inders
    0.08
    eric
    0.08
    ยà¸Ļà¸ķà¹Į
    0.08
    INDER
    0.08
    anity
    0.08
    -shaped
    0.07
    à¸Ńำà¸Ļาà¸Ī
    0.07
    Activations Density 0.009%

    No Known Activations