© 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. 18255
    Prev
    Next
    INDEX
    Explanations

    structure with

    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
    ลà¹Į
    -0.09
    assar
    -0.09
    ows
    -0.09
    ª
    -0.09
    สะà¸Ķวà¸ģ
    -0.08
    itory
    -0.08
    entifier
    -0.08
    imizer
    -0.08
    owed
    -0.08
    ición
    -0.08
    POSITIVE LOGITS
     timeval
    0.12
     timespec
    0.11
    urally
    0.10
    less
    0.09
    ÙħÙĨد
    0.09
    tte
    0.09
     اÙĦتØŃتÙĬØ©
    0.08
     kiá»ĩn
    0.08
    pile
    0.08
    halb
    0.08
    Activations Density 0.077%

    No Known Activations