© 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. 61593
    Prev
    Next
    INDEX
    Explanations

    gene. PE

    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
    itions
    -0.09
    羽翼
    -0.06
    æĢĢæĬ±
    -0.06
    à¸Ńา
    -0.06
    ene
    -0.06
    æµ
    -0.06
    åIJī
    -0.06
    æ²³éķĩ
    -0.06
    èݺ
    -0.06
    aix
    -0.06
    POSITIVE LOGITS
    å¾·éŁ³
    0.08
    ()(
    0.07
     belas
    0.07
    идÑĥ
    0.07
    inken
    0.07
    åĮĨ
    0.07
    midd
    0.07
    gradu
    0.06
    дик
    0.06
    vard
    0.06
    Activations Density 0.002%

    No Known Activations