© 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. 34212
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    strup
    -0.07
     Waterloo
    -0.07
    ergen
    -0.07
    -ring
    -0.07
    -opacity
    -0.07
    mund
    -0.07
    edx
    -0.07
    -len
    -0.07
     <<-
    -0.07
    -begin
    -0.07
    POSITIVE LOGITS
    XA
    0.07
    å°±è§ģ
    0.07
    коÑĢ
    0.06
    zub
    0.06
    olor
    0.06
    ä¸ºä½łæݨèįIJ
    0.06
    æĬĢæľ¯çŃī
    0.06
    elai
    0.06
    ÑĢоÑģ
    0.06
     Sec
    0.06
    Activations Density 1.960%

    No Known Activations