© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9113
    Prev
    Next
    INDEX
    Explanations

    partition, coefficients, sensation

    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
    enet
    -0.09
    ANDO
    -0.08
    æľī家
    -0.07
    سر
    -0.07
    عÙĨ
    -0.07
    itik
    -0.07
    åĿŀ
    -0.07
    icot
    -0.07
    à¹Īาà¸Ļ
    -0.07
    opher
    -0.07
    POSITIVE LOGITS
    å¸ķ
    0.08
    ushman
    0.07
    cep
    0.07
    éĶ¦
    0.07
    ạm
    0.07
    ç²ī
    0.06
    )?$
    0.06
     Rail
    0.06
     اÙĦØ£ÙĦ
    0.06
    lier
    0.06
    Activations Density 0.177%

    No Known Activations