© 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. 4796
    Prev
    Next
    INDEX
    Explanations

    options in parentheses

    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
    ses
    -0.08
    DbType
    -0.08
     Renov
    -0.08
    umul
    -0.08
    bish
    -0.08
    schlä
    -0.07
    ofer
    -0.07
    âĢ¦),
    -0.07
    issons
    -0.07
    scher
    -0.07
    POSITIVE LOGITS
    deka
    0.06
    以ä¸Ĭ
    0.06
    ↵↵
    0.06
    akis
    0.06
    osso
    0.06
    icans
    0.06
    çľĭä¸Ģçľ¼
    0.06
     Hint
    0.06
    Õ¡Õ¯
    0.06
    Ĭ
    0.06
    Activations Density 0.011%

    No Known Activations