© 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. 37510
    Prev
    Next
    INDEX
    Explanations

    language and queries

    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
    žu
    -0.09
    hiba
    -0.09
     تØŃص
    -0.09
    UnderTest
    -0.08
    åIJįå½ķ
    -0.08
     Legislat
    -0.08
    ssel
    -0.08
    plr
    -0.08
    ersh
    -0.08
    stras
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶
    0.07
    åıĻè¿°
    0.07
     prose
    0.07
    çļĦèĩªçĦ¶
    0.07
     spoken
    0.07
    åıĻ
    0.07
    æķĺ
    0.07
     language
    0.07
     sentence
    0.07
    æııè¿°
    0.07
    Activations Density 0.017%

    No Known Activations