© 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. 25466
    Prev
    Next
    INDEX
    Explanations

    spatial frequency, units, namespace

    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
    êu
    -0.08
     úl
    -0.08
    пÑĮ
    -0.08
    диÑĤелÑĮ
    -0.07
     Pruitt
    -0.07
    úa
    -0.07
    ñez
    -0.07
     Replica
    -0.07
    epro
    -0.07
     TÃī
    -0.07
    POSITIVE LOGITS
    roe
    0.08
    fat
    0.06
    -fat
    0.06
    åį³ä½į
    0.06
    .jp
    0.06
    bill
    0.06
    åķĨæĬ¥
    0.06
    nth
    0.06
    对å¤ĸ
    0.06
    åĻ¢
    0.06
    Activations Density 0.002%

    No Known Activations