© 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. 45975
    Prev
    Next
    INDEX
    Explanations

    deal update

    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
    алан
    -0.09
    lexer
    -0.08
    ugins
    -0.08
    irut
    -0.08
    á»ĩt
    -0.08
    krat
    -0.08
     disastr
    -0.08
    oker
    -0.08
    adiens
    -0.08
    å±ķå¼Ģåħ¨æĸĩ
    -0.08
    POSITIVE LOGITS
     bare
    0.06
     forever
    0.06
     bil
    0.06
    asa
    0.06
     lateral
    0.06
     c
    0.06
     إبر
    0.06
    -
    0.06
    (
    0.06
    亿
    0.05
    Activations Density 0.047%

    No Known Activations