© 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. 61399
    Prev
    Next
    INDEX
    Explanations

    list items with commas

    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
     latter
    -0.07
    åīįèĢħ
    -0.07
    åIJİèĢħ
    -0.07
    ä¸īèĢħ
    -0.07
    ucker
    -0.07
    Slash
    -0.07
    !.
    -0.07
     (()
    -0.07
    cape
    -0.06
    ota
    -0.06
    POSITIVE LOGITS
    ached
    0.07
    åıĮ羸
    0.07
    gra
    0.07
     '_',
    0.07
    AMI
    0.07
    alloca
    0.07
    _counters
    0.07
    .generated
    0.06
    æ¯Ķå¦Ĥ说
    0.06
    stood
    0.06
    Activations Density 0.027%

    No Known Activations