© 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. 21191
    Prev
    Next
    INDEX
    Explanations

    integrating from 0

    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
    agre
    -0.08
     roma
    -0.08
    finale
    -0.07
    iera
    -0.07
    åľ¨ä¸»
    -0.07
    itals
    -0.07
    obie
    -0.07
     agre
    -0.07
    æ±ĩæĢ»è¡¨
    -0.07
    باء
    -0.07
    POSITIVE LOGITS
    ignet
    0.08
    Middle
    0.07
     middle
    0.07
    çļĦä¸Ń
    0.07
    middle
    0.07
    ignano
    0.07
    olong
    0.07
    æľªåħį
    0.07
    ulg
    0.07
     fellow
    0.07
    Activations Density 0.009%

    No Known Activations