© 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. 13152
    Prev
    Next
    INDEX
    Explanations

    comparison functions

    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
    ÅĦczy
    -0.11
    inach
    -0.08
    onen
    -0.08
    itionally
    -0.08
     altogether
    -0.07
    itles
    -0.07
    à´Ļàµįà´ķ
    -0.07
     поÑĩа
    -0.07
    DataURL
    -0.07
    curso
    -0.07
    POSITIVE LOGITS
    strcmp
    0.07
    strncmp
    0.07
    memcmp
    0.07
    æİĸ
    0.06
    ru
    0.06
     compar
    0.06
     Gle
    0.06
    alon
    0.06
    线ä¸Ĭ线
    0.06
     Comparator
    0.06
    Activations Density 0.007%

    No Known Activations