© 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. 25543
    Prev
    Next
    INDEX
    Explanations

    technical terms, group names, and specific roles

    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
    -0.06
     l
    -0.06
     i
    -0.06
     en
    -0.05
    ij
    -0.05
     /
    -0.05
    ↵
    -0.05
     ,
    -0.05
    ventional
    -0.05
     '
    -0.05
    POSITIVE LOGITS
     sema
    0.10
    á»ķi
    0.09
    Äħcz
    0.09
    ndo
    0.08
    åı¯æ¢¦
    0.08
    utkan
    0.08
    ÙĪزÙĩ
    0.08
    Verdana
    0.08
    idge
    0.08
    à¸Ĺà¹Į
    0.08
    Activations Density 0.140%

    No Known Activations