© 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. 50855
    Prev
    Next
    INDEX
    Explanations

    vehicle lane maneuvers

    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
    å°ģåŃĺ
    -0.08
     تاب
    -0.08
    endis
    -0.07
    è·ijèħ¿
    -0.07
     kì
    -0.07
    runner
    -0.07
    å¥Ķæ³¢
    -0.07
    inscrire
    -0.07
    cach
    -0.07
    esch
    -0.06
    POSITIVE LOGITS
    礼让
    0.10
    çĽ²åĮº
    0.09
     maneuvers
    0.09
     instinct
    0.08
    ูà¹Ī
    0.08
    urre
    0.08
    ä½İéĢŁ
    0.08
     overt
    0.08
    éģ¿è®©
    0.08
    示æĦı
    0.08
    Activations Density 0.022%

    No Known Activations