© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38259
    Prev
    Next
    INDEX
    Explanations

    advertisement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    zir
    -0.07
    _symbols
    -0.07
    -0.07
    ắt
    -0.07
    zb
    -0.07
    ylon
    -0.07
    计ç®Ĺæľºè½¯ä»¶
    -0.07
    åģıåģı
    -0.07
     distrib
    -0.06
     distributors
    -0.06
    POSITIVE LOGITS
    격ìĿĦ
    0.07
    祺
    0.07
     epil
    0.07
    عÙħ
    0.07
    rophic
    0.06
    ences
    0.06
    patch
    0.06
    äºĨä¸Ģéģĵ
    0.06
    çŃı
    0.06
    acto
    0.06
    Activations Density 0.001%

    No Known Activations