© 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. 24083
    Prev
    Next
    INDEX
    Explanations

    high-speed rail and trains

    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
    ÅĤo
    -0.06
    éĵ¸éĵģ
    -0.06
     dip
    -0.06
     пеÑĢео
    -0.06
     pi
    -0.06
    æĬ±
    -0.06
     primordial
    -0.06
    aget
    -0.06
    ima
    -0.06
    ä¸ĩèĥ½
    -0.06
    POSITIVE LOGITS
     speeds
    0.09
    speed
    0.09
     speed
    0.09
    éĢŁåº¦
    0.09
    Speed
    0.08
     tá»ijc
    0.08
    peed
    0.08
    æľįåĬ¡ä¿Ŀéļľ
    0.08
     Speed
    0.08
    wave
    0.08
    Activations Density 0.016%

    No Known Activations