© 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. 34547
    Prev
    Next
    INDEX
    Explanations

    programme numbers

    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
    ighbor
    -0.08
     utilized
    -0.08
    ÈĻ
    -0.08
     ÈĻ
    -0.08
     utilize
    -0.08
     neighborhood
    -0.08
    ÄĥÈĻ
    -0.08
    &m
    -0.07
     utilizes
    -0.07
     behaviors
    -0.07
    POSITIVE LOGITS
    aviour
    0.10
    avour
    0.09
     fulfil
    0.09
     armour
    0.09
    èĩ³æĸ¼
    0.09
     ÑĩÑijм
    0.09
     اÙĦتÙī
    0.09
     programmes
    0.08
     recognised
    0.08
     favour
    0.08
    Activations Density 0.398%

    No Known Activations