© 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. 44314
    Prev
    Next
    INDEX
    Explanations

    table separators |+-+

    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
    é¢ĨåħĪ
    -0.07
    icals
    -0.07
    aday
    -0.07
    ׾×ij
    -0.07
    idane
    -0.07
    stras
    -0.07
    iforn
    -0.07
    éz
    -0.07
    ec
    -0.07
    rikes
    -0.07
    POSITIVE LOGITS
    Med
    0.07
    (SP
    0.07
    èįĨæ£ĺ
    0.07
     Desp
    0.06
    ध
    0.06
    ä»ĸçļĦ人
    0.06
    å²Ĺ
    0.06
     Med
    0.06
     méd
    0.06
    润泽
    0.06
    Activations Density 0.002%

    No Known Activations