© 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. 23896
    Prev
    Next
    INDEX
    Explanations

    endif

    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
    家æĿij
    -0.07
    ãģĿãģĨãģ§
    -0.07
    apus
    -0.07
    ấn
    -0.06
     otherwise
    -0.06
     Spur
    -0.06
    åIJ¦åĪĻä¼ļ
    -0.06
    zyn
    -0.06
    FromString
    -0.06
    se
    -0.06
    POSITIVE LOGITS
    imizer
    0.07
    chin
    0.07
    ÑijÑĢ
    0.07
    ybrid
    0.06
     Budd
    0.06
    cli
    0.06
    rov
    0.06
    æ¯Ķ以åīį
    0.06
    rics
    0.06
    пÑĭ
    0.06
    Activations Density 0.036%

    No Known Activations