© 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. 59058
    Prev
    Next
    INDEX
    Explanations

    studied, established, discussed

    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
    ptype
    -0.08
    mlin
    -0.08
    OLON
    -0.08
    odle
    -0.08
    æīĢ欲è¨Ģ
    -0.08
    ---</
    -0.08
    eliz
    -0.08
    ouvel
    -0.08
    .Results
    -0.08
    à¹ģร
    -0.08
    POSITIVE LOGITS
    0.07
    çĶ¨åľ¨
    0.07
    x
    0.07
    以å¤ĩ
    0.06
    needed
    0.06
     used
    0.06
    çĭ¬ç«ĭ
    0.06
     ref
    0.06
     separately
    0.06
    ä¹ĭåīįåľ¨
    0.06
    Activations Density 0.297%

    No Known Activations