© 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. 56456
    Prev
    Next
    INDEX
    Explanations

    sequences of C's and 0's

    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
    áz
    -0.07
     backwards
    -0.06
    并åIJĮæŶ
    -0.06
    èįŁ
    -0.06
    auer
    -0.06
    inh
    -0.06
    orme
    -0.06
    ä»İåīį
    -0.06
    arr
    -0.06
    icon
    -0.06
    POSITIVE LOGITS
    falt
    0.08
    dden
    0.08
    anzo
    0.07
    ิà¸Ķ
    0.07
    idge
    0.07
    æļĹ
    0.07
    WithURL
    0.07
    家ä¹IJ
    0.07
    edd
    0.07
    !--
    0.07
    Activations Density 0.009%

    No Known Activations