© 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. 64578
    Prev
    Next
    INDEX
    Explanations

    initialization and setup code

    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
    íĦ¸
    -0.07
    basis
    -0.07
    atomy
    -0.07
    andone
    -0.07
    aries
    -0.07
     sweat
    -0.06
    à¹Ħà¸ĭà¸ķà¹Į
    -0.06
    .gnu
    -0.06
    é«ĺåİĭ
    -0.06
     Geç
    -0.06
    POSITIVE LOGITS
     inputs
    0.08
     initialised
    0.07
    è¢
    0.07
    åĩĨå¤ĩ好çļĦ
    0.07
     input
    0.07
     initData
    0.07
    ogle
    0.07
    illow
    0.07
     eventData
    0.07
    æĵį
    0.07
    Activations Density 0.001%

    No Known Activations