© 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. 22555
    Prev
    Next
    INDEX
    Explanations

    distance, speed, and units

    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
    çļĦ主ä½ĵ
    -0.09
    主ä½ĵçļĦ
    -0.08
    主ä½ĵ
    -0.08
     Rit
    -0.08
    为主ä½ĵ
    -0.08
    天åħĥ
    -0.08
    ocs
    -0.07
    aleb
    -0.07
    为主ä½ĵçļĦ
    -0.07
    anzo
    -0.07
    POSITIVE LOGITS
    ä¸Ģ度çļĦ
    0.07
    è·¨è¶Ĭ
    0.07
    ä¸Ģåı£æ°Ķ
    0.06
    åįĩéĻį
    0.06
    è°ĥçłĶåijĺ
    0.06
     Ø¢Ùħ
    0.06
    跨度
    0.06
    温差
    0.06
     range
    0.06
    ä¸Ĭæµ®
    0.06
    Activations Density 0.008%

    No Known Activations