© 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. 59774
    Prev
    Next
    INDEX
    Explanations

    better than those

    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
    ä¿¡æģ¯çĶ±
    -0.08
    sst
    -0.08
    enis
    -0.07
     \`
    -0.07
    IGH
    -0.07
    елÑĮ
    -0.07
     ìĪĺë°ĸìĹIJ
    -0.07
    VRT
    -0.07
    du
    -0.07
    amp
    -0.07
    POSITIVE LOGITS
    èį¡æ¼¾
    0.07
    teres
    0.07
    jav
    0.07
    å¥İ
    0.06
    æĹłæģĻ
    0.06
     claimed
    0.06
    åĪļæīį
    0.06
    amma
    0.06
    æĪij们æīĢ
    0.06
    cratch
    0.06
    Activations Density 0.005%

    No Known Activations