© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64019
    Prev
    Next
    INDEX
    Explanations

    if.. daily

    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
    ãĢijãĢIJ
    -0.08
    åħ³æ³¨åħ¬ä¼Ĺåı·
    -0.07
    à¹Į
    -0.07
    ÛĮÙģ
    -0.07
    纳德
    -0.07
    repid
    -0.07
     shaved
    -0.07
    à¥ĩम
    -0.07
    ãĥ«ãĥķ
    -0.07
    à¤ķि
    -0.07
    POSITIVE LOGITS
     Redistributions
    0.08
    ãm
    0.07
    {/
    0.07
    wagen
    0.07
    å¹ķ
    0.07
    нÑĥ
    0.07
    RIA
    0.07
    able
    0.06
    oš
    0.06
     endlich
    0.06
    Activations Density 0.078%

    No Known Activations