© 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. 37607
    Prev
    Next
    INDEX
    Explanations

    capacitance, ratio, exponent, ID, length, properties, context, Q, impedance

    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
    Negative Logits
    éĢĤåIJĪçļĦ
    -0.08
    blr
    -0.08
    ubi
    -0.07
    มูล
    -0.07
    èĻ½æľī
    -0.07
    amd
    -0.07
    溪水
    -0.07
     تÙĤرÙĬب
    -0.07
    anel
    -0.07
    pool
    -0.07
    POSITIVE LOGITS
    æĺ±
    0.08
    å®ļéĩı
    0.07
    è¶Ĭæĺ¯
    0.06
    çijľ
    0.06
    uken
    0.06
     колиÑĩ
    0.06
    è¶Ĭ大
    0.06
    äºĨçļĦ
    0.06
    æĹ¢æĺ¯
    0.06
    Greater
    0.06
    Activations Density 0.011%

    No Known Activations