© 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. 61100
    Prev
    Next
    INDEX
    Explanations

    left or right body parts

    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
    ļ
    -0.08
    emin
    -0.07
    eder
    -0.07
    pite
    -0.07
    anken
    -0.07
    -like
    -0.07
    çĬ¶
    -0.07
    åĪ°åŃ¦æł¡
    -0.06
    uite
    -0.06
    庸
    -0.06
    POSITIVE LOGITS
    为主çļĦ
    0.08
    为主
    0.08
    鬱
    0.07
    /left
    0.07
    lingen
    0.07
    à¹Ģà¸Ľà¹ĩà¸Ļหลัà¸ģ
    0.07
    voud
    0.07
    çĤºä¾ĭ
    0.07
    (right
    0.07
    /right
    0.07
    Activations Density 0.090%

    No Known Activations