© 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. 34498
    Prev
    Next
    INDEX
    Explanations

    children with conditions

    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
    žel
    -0.07
    presso
    -0.07
    URIComponent
    -0.07
    ÙĪÙĥ
    -0.07
    оÑıÑĤ
    -0.07
    .define
    -0.06
    ¹Ħ
    -0.06
    lom
    -0.06
    .relative
    -0.06
    åĬłåĪĨ
    -0.06
    POSITIVE LOGITS
    å½ĵä¸Ģ个
    0.11
    åĽł
    0.11
    ä¸ĢæĹ¦è¢«
    0.10
     suspected
    0.10
     failing
    0.10
    å¦Ĥæŀľä¸Ģ个
    0.10
    .failed
    0.09
    ä¸ĢæŦåıijçĶŁ
    0.09
    _failed
    0.09
    ä¸įåIJĪæł¼çļĦ
    0.09
    Activations Density 0.922%

    No Known Activations