© 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. 18090
    Prev
    Next
    INDEX
    Explanations

    marked cars

    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
    Âł
    -0.06
    åľ°éĩĮ
    -0.06
    å±ĭéĩĮ
    -0.06
    æľīäºĽäºĭ
    -0.06
    åĩij
    -0.06
    FML
    -0.06
    èµ°è¿Ľ
    -0.06
    -0.06
     odds
    -0.06
    ä»İå°ıåĪ°å¤§
    -0.06
    POSITIVE LOGITS
    داد
    0.09
    bogen
    0.09
    OrCreate
    0.09
     sejauh
    0.08
     Previd
    0.08
    itik
    0.08
     обознаÑĩа
    0.08
    uard
    0.08
    ignum
    0.08
     Pellegr
    0.08
    Activations Density 0.004%

    No Known Activations