© 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. 61174
    Prev
    Next
    INDEX
    Explanations

    size, empty

    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
    ланд
    -0.08
    ypo
    -0.08
    ä¿Ŀå®Ī
    -0.08
    urning
    -0.07
    edizione
    -0.07
    æĺ¯éĤ£ä¹Ī
    -0.07
    ÑģÑĤви
    -0.07
    失è°ĥ
    -0.07
    oust
    -0.07
    Revision
    -0.07
    POSITIVE LOGITS
     unless
    0.08
    æľĢ令人
    0.07
     if
    0.06
    容
    0.06
    ali
    0.06
     concern
    0.06
    å®Ŀè´µçļĦ
    0.06
     hom
    0.06
    unless
    0.06
    ä¸įåºĶ该
    0.06
    Activations Density 0.122%

    No Known Activations