© 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. 13505
    Prev
    Next
    INDEX
    Explanations

    rounding or time

    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
    迹
    -0.09
     Indoor
    -0.09
    à·Ģà·ı
    -0.08
    _TP
    -0.08
    irat
    -0.08
     Vert
    -0.08
     vit
    -0.07
    inari
    -0.07
    áĥĶáĥľ
    -0.07
    .inverse
    -0.07
    POSITIVE LOGITS
    _bias
    0.07
    ä¸ĢåįĬ
    0.07
    åIJĨ
    0.07
    ä¸īæĽ´
    0.07
    dz
    0.07
    çļĦæłĩåĩĨ
    0.06
    .std
    0.06
    åı¦ä¸ĢåįĬ
    0.06
    echa
    0.06
     Criterion
    0.06
    Activations Density 0.006%

    No Known Activations