© 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. 43598
    Prev
    Next
    INDEX
    Explanations

    detailed diagrams

    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
    è¿ĶåĽŀåĪĹ表
    -0.08
    èĪį
    -0.07
     bel
    -0.07
    对å¸Ĥåľº
    -0.07
    åĿĩåĮĢ
    -0.07
    ysh
    -0.07
    herits
    -0.07
     Bel
    -0.07
    achel
    -0.06
    å¸ĤåľºéľĢæ±Ĥ
    -0.06
    POSITIVE LOGITS
    etailed
    0.08
     diagrams
    0.08
     detailed
    0.08
    大èį¯æĪ¿
    0.07
     arrows
    0.07
    atom
    0.07
     Detailed
    0.07
     diagram
    0.07
    çĶ»æ³ķ
    0.07
     intricate
    0.07
    Activations Density 0.003%

    No Known Activations