© 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. 21053
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and specific entities

    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
     ÑĤÑĢÑĥдо
    -0.09
     advoc
    -0.08
    åIJ¬åĻ¨
    -0.08
    çIJĨè®ºåŁºç¡Ģ
    -0.08
    صÙģ
    -0.08
    icismo
    -0.08
    Brain
    -0.07
    åĨ·éŨ
    -0.07
    çļĦè®®æ¡Ī
    -0.07
    彦
    -0.07
    POSITIVE LOGITS
     ekst
    0.07
     relation
    0.07
     ont
    0.07
     logos
    0.07
     Relation
    0.07
     Gad
    0.07
     provisional
    0.07
     presup
    0.07
     creature
    0.07
     pregnant
    0.07
    Activations Density 0.034%

    No Known Activations