© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51940
    Prev
    Next
    INDEX
    Explanations

    railway transport

    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
    agua
    -0.08
    alit
    -0.08
    ä½Ļåľ°
    -0.08
     diety
    -0.08
    repid
    -0.08
    åı¸éķ¿
    -0.08
    æľ¬æĸĩ为åįļ主
    -0.07
    combe
    -0.07
    ãĤĵãģª
    -0.07
    禺
    -0.07
    POSITIVE LOGITS
    roads
    0.09
    iog
    0.07
    ymar
    0.07
    å·¥ä½ľèĢħ
    0.07
    -mounted
    0.07
    sWith
    0.07
    onne
    0.07
    å½ĵå±Ģ
    0.07
    yards
    0.06
    جة
    0.06
    Activations Density 0.043%

    No Known Activations