© 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. 58938
    Prev
    Next
    INDEX
    Explanations

    aptamer, qubit, sinkholes, dispensary

    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
    itionen
    -0.10
    iveness
    -0.09
    дви
    -0.07
    ãĥĵãĥ³ãĤ°
    -0.07
    å°½æľī
    -0.07
    èģĮä¸ļåѦéĻ¢
    -0.07
    prus
    -0.07
    curring
    -0.07
    êµī
    -0.07
    ulations
    -0.07
    POSITIVE LOGITS
    atch
    0.08
    aph
    0.07
    æīĭä¸ŃçļĦ
    0.07
    ÑĤелÑĮ
    0.07
    olum
    0.07
    ð
    0.07
    ellite
    0.07
    ä¹ĭä¸ĢçļĦ
    0.07
    èij
    0.07
    sole
    0.06
    Activations Density 0.315%

    No Known Activations