© 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. 64280
    Prev
    Next
    INDEX
    Explanations

    geological/seismic concepts

    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
     dụ
    -0.08
    edImage
    -0.08
    à¹Ģวียà¸Ļ
    -0.08
    åĴĮæĶ¹è¿Ľ
    -0.07
    缴æİ¥æĪĸ
    -0.07
    edge
    -0.07
    داب
    -0.07
    stv
    -0.07
    inage
    -0.07
    NCY
    -0.07
    POSITIVE LOGITS
    quake
    0.09
    åŃ¦å®¶
    0.08
    åĭĺæİ¢
    0.08
    åľ°è²Į
    0.08
    ures
    0.07
    othy
    0.07
    าะ
    0.07
    urts
    0.07
    æľīå¿ĥ人
    0.07
    hower
    0.07
    Activations Density 0.015%

    No Known Activations