© 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. 43903
    Prev
    Next
    INDEX
    Explanations

    resistor electrical components

    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
    èĦ¯
    -0.07
     Poly
    -0.07
    ä¸ĩäºĭ
    -0.07
    ogos
    -0.07
    解éļ¾
    -0.07
    èĦĨ
    -0.07
    离ä¸įå¼Ģ
    -0.06
    kker
    -0.06
    sorted
    -0.06
    åīįåįģ
    -0.06
    POSITIVE LOGITS
    å·´æĭī
    0.10
     splitter
    0.10
    è¿ŀæİ¥åĪ°
    0.08
    Split
    0.08
    uard
    0.08
     split
    0.08
    éĥ½å¤Ħäºİ
    0.07
    æĪĺçķ¥æĢ§
    0.07
    åĨħå¤ĸ
    0.07
     Split
    0.07
    Activations Density 0.004%

    No Known Activations