© 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. 31474
    Prev
    Next
    INDEX
    Explanations

    ianorte, riel Scorodomoff, SNZ, !defined

    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
    agne
    -0.08
     aggregated
    -0.08
    å°ģåłµ
    -0.07
    йÑģ
    -0.07
     collaps
    -0.07
    ebt
    -0.07
    产åĵģç±»åŀĭ
    -0.07
    éĺĢ
    -0.07
    yce
    -0.07
     extinct
    -0.07
    POSITIVE LOGITS
     Zem
    0.08
     bantu
    0.07
    ENSOR
    0.07
    çİ»
    0.07
    physics
    0.07
    åħīæ»ij
    0.07
    çī©çIJĨåѦ
    0.07
    ouser
    0.07
    ä¸ĩåį·
    0.07
    sandbox
    0.07
    Activations Density 0.002%

    No Known Activations