© 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. 61239
    Prev
    Next
    INDEX
    Explanations

    zero or 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
    erah
    -0.07
     primitive
    -0.07
    primitive
    -0.07
    رس
    -0.07
     primit
    -0.07
    udeau
    -0.07
    opping
    -0.07
    inius
    -0.07
    ulton
    -0.07
    à¸Ĥาà¸Ķ
    -0.07
    POSITIVE LOGITS
    ä¸ºéĽ¶
    0.22
     zero
    0.20
    鼶
    0.19
    zero
    0.19
     Zero
    0.19
    Zero
    0.18
    -zero
    0.17
     ZERO
    0.17
    _zero
    0.17
    ãĤ¼ãĥŃ
    0.16
    Activations Density 0.142%

    No Known Activations