© 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. 44111
    Prev
    Next
    INDEX
    Explanations

    ET al. and Nordlund LM

    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
    arness
    -0.07
    engel
    -0.07
    hdl
    -0.07
     Ly
    -0.06
    说è¯ĿçļĦ
    -0.06
    holt
    -0.06
    æµħæµħ
    -0.06
    åĦ¿
    -0.06
    说æĺ¯
    -0.06
     aval
    -0.06
    POSITIVE LOGITS
    åı¤ä»£
    0.07
    onis
    0.07
    ãĥĸãĥŃ
    0.07
    çĤľ
    0.07
     homeschool
    0.07
    æģ¢
    0.07
    à´ķàµį
    0.07
    æľĢåħ¨
    0.07
    亲çĪ±çļĦåIJĮåѦ们
    0.07
    çģ«æĬĬ
    0.07
    Activations Density 0.001%

    No Known Activations