© 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. 31977
    Prev
    Next
    INDEX
    Explanations

    quantifiable measurements or identifiers

    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
    aData
    -0.08
    "<?
    -0.08
    ä¸Ģåİ»
    -0.07
    {}.
    -0.07
    Wunused
    -0.07
    eze
    -0.07
    ij¸
    -0.07
    ä¸Ģç¼ķ
    -0.07
    /XMLSchema
    -0.07
    :type
    -0.07
    POSITIVE LOGITS
    åĨ³å®ļäºĨ
    0.08
     varies
    0.07
     matches
    0.07
    åĪļ好
    0.07
    åĴĮåĨħ容
    0.07
    åĨ³å®ļçļĦ
    0.06
    åıĸåĨ³äºİ
    0.06
    éĢļ天
    0.06
    å®ļ为
    0.06
    ç¡®å®ļ为
    0.06
    Activations Density 0.102%

    No Known Activations