© 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. 19152
    Prev
    Next
    INDEX
    Explanations

    LEGO needs

    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
    iven
    -0.07
    éĢīçĶ¨
    -0.07
    åģľ
    -0.06
    åľ£å¥³
    -0.06
    åĪĨ
    -0.06
    æĺ¯ä¸Ģæľ¬
    -0.06
     hast
    -0.06
    å¿Į
    -0.06
    Authors
    -0.06
    ç¥ĸ
    -0.06
    POSITIVE LOGITS
    menti
    0.08
    loh
    0.07
    tan
    0.07
    çļĦé»Ħéĩij
    0.07
     بس
    0.07
     tan
    0.07
    ìĨĮ리
    0.07
    æīİæīİå®ŀ
    0.07
    ä¹Łåıªæľī
    0.07
    vet
    0.07
    Activations Density 0.001%

    No Known Activations