© 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. 28413
    Prev
    Next
    INDEX
    Explanations

    things following "things"

    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
    istar
    -0.08
    edig
    -0.08
    estal
    -0.08
    ocy
    -0.07
    æ´ĭæ´ĭ
    -0.07
    egram
    -0.07
    西æĸ¯
    -0.07
    éħ®
    -0.07
    à¸ļà¹īาà¸ĩ
    -0.07
    èīĩ
    -0.07
    POSITIVE LOGITS
    wiÅĽcie
    0.10
     else
    0.09
    ÙĬØŃ
    0.08
    -même
    0.08
    ummy
    0.07
    /people
    0.07
     annat
    0.07
    czas
    0.07
    aut
    0.07
    aa
    0.07
    Activations Density 0.155%

    No Known Activations