© 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. 24353
    Prev
    Next
    INDEX
    Explanations

    JSON data and its context

    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
    TextWriter
    -0.07
    inek
    -0.07
    èĤ¯å®ļçļĦ
    -0.07
    ä¸ĢçĶŁä¸Ń
    -0.07
    éĹ´çļĦ
    -0.06
     verko
    -0.06
    è´¹
    -0.06
    å¦ĤæŀľæĤ¨å¯¹
    -0.06
    ndef
    -0.06
    ucs
    -0.06
    POSITIVE LOGITS
     input
    0.12
    è¾ĵåħ¥
    0.12
     Input
    0.10
    ä¼łåħ¥
    0.10
    è¾ĵåħ¥çļĦ
    0.10
    input
    0.09
     supplied
    0.09
    Input
    0.09
     Provided
    0.09
     inputs
    0.09
    Activations Density 0.062%

    No Known Activations