© 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. 46991
    Prev
    Next
    INDEX
    Explanations

    First Circuit

    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
    å¾·éĺ³
    -0.09
     Broncos
    -0.09
     Denver
    -0.08
     Duis
    -0.08
    åıĮæµģ
    -0.08
    èľĢ
    -0.08
    æ¸ŃåįĹ
    -0.08
     Köl
    -0.08
    Colorado
    -0.08
    airo
    -0.08
    POSITIVE LOGITS
     Massachusetts
    0.16
     Boston
    0.15
    Boston
    0.15
    波士顿
    0.14
    麻çľģ
    0.13
    achusetts
    0.11
    /MIT
    0.11
     Maine
    0.11
     Celtics
    0.11
    èĬ¬åħ°
    0.10
    Activations Density 0.994%

    No Known Activations