© 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. 59016
    Prev
    Next
    INDEX
    Explanations

    like this or code

    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
    SSI
    -0.07
    abling
    -0.07
    ore
    -0.07
    elic
    -0.07
    quip
    -0.06
    arg
    -0.06
    æĿĤ
    -0.06
    avig
    -0.06
    éĢļåĬĽ
    -0.06
    åħįéĻ¤
    -0.06
    POSITIVE LOGITS
    дик
    0.08
    æĹ¢çĦ¶æĺ¯
    0.08
    Began
    0.07
    åĪĿæŃ¥
    0.07
    åĪ«è®©
    0.07
    æ¶īåıĬ
    0.07
    sche
    0.07
    odox
    0.07
    æĸ°æ°Ķ象
    0.07
    ä¸įå®ļ
    0.07
    Activations Density 0.005%

    No Known Activations