© 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. 8340
    Prev
    Next
    INDEX
    Explanations

    magnetic field strength and frequency

    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
    æ¸ł
    -0.06
    çĬ¶çļĦ
    -0.06
     kop
    -0.06
    çĭĢ
    -0.06
     prog
    -0.06
    éĿŀçī©è´¨
    -0.06
    hood
    -0.06
    æĹ©çĿ¡
    -0.06
    æ¡Ĩ
    -0.06
     ab
    -0.05
    POSITIVE LOGITS
    æīĢ使çĶ¨çļĦ
    0.08
    standard
    0.08
    quartered
    0.08
    æīĢçĶ¨
    0.08
     flagship
    0.08
    ìĿ´ë²Ħ
    0.08
    vente
    0.08
    æ¨Ļæºĸ
    0.08
    _ARG
    0.08
    uste
    0.08
    Activations Density 0.106%

    No Known Activations