© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10984
    Prev
    Next
    INDEX
    Explanations

    like after name

    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
    usc
    -0.07
    usco
    -0.07
    anos
    -0.07
    æīĢåIJ¸å¼ķ
    -0.06
    æĹłåıį
    -0.06
    лдÑĭ
    -0.06
     ne
    -0.06
    amba
    -0.06
    APAN
    -0.06
    perimental
    -0.06
    POSITIVE LOGITS
    tiv
    0.07
    åıĪæľī
    0.07
    ond
    0.07
    _activ
    0.07
    åĿĬ
    0.07
     again
    0.06
    atos
    0.06
    Ñģила
    0.06
     seventh
    0.06
    utip
    0.06
    Activations Density 0.019%

    No Known Activations