© 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. 44501
    Prev
    Next
    INDEX
    Explanations

    for + noun/suffix

    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
    chos
    -0.07
    ä¸įä¸Ĭ
    -0.07
    าว
    -0.06
    жением
    -0.06
    ç¬ijåĤ²
    -0.06
    essus
    -0.06
    à¸Īุà¸Ķ
    -0.06
    åĨ²åIJij
    -0.06
    awah
    -0.06
    à¹Ĩ
    -0.06
    POSITIVE LOGITS
    acus
    0.09
    è¿Ľä¸ĢæŃ¥çļĦ
    0.08
     ÙħزÙĬد
    0.08
    å®Įåħ¨çļĦ
    0.08
    ister
    0.08
    åħ·ä½ĵåĪĨæŀIJ
    0.07
     continual
    0.07
    er
    0.07
    estruct
    0.07
    è¿Ľä¸ĢæŃ¥
    0.07
    Activations Density 0.208%

    No Known Activations