© 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. 60107
    Prev
    Next
    INDEX
    Explanations

    your opinion or suggestions

    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
    åĽ
    -0.07
    Ø©
    -0.07
    APS
    -0.07
    ãģıãĤĮ
    -0.07
    Ñĥго
    -0.06
    追æ±Ĥåįĵè¶Ĭ
    -0.06
    rasz
    -0.06
    hta
    -0.06
    orta
    -0.06
    æĮĩå®ļçļĦ
    -0.06
    POSITIVE LOGITS
    lems
    0.08
    å¾ij
    0.07
    åŃ¦æł¡åľ¨
    0.07
    robi
    0.07
    å¾Ħ
    0.07
    à´¤àµį
    0.07
     freely
    0.07
    éĢļè¿ĩ以ä¸Ĭ
    0.07
    isman
    0.07
    ingt
    0.07
    Activations Density 0.012%

    No Known Activations