© 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. 55917
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a unit

    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
    oplast
    -0.08
    hoff
    -0.08
    åĩłçĻ¾
    -0.08
    uppy
    -0.07
    ä¸ĩæĴŃæĶ¾
    -0.07
    åįĥçĻ¾
    -0.07
    åħ¶çī¹å¾ģ
    -0.07
    æľŁåĴĮ
    -0.07
    bacher
    -0.07
    lund
    -0.07
    POSITIVE LOGITS
    以åĨħçļĦ
    0.09
    ä¹ĭæķ°
    0.09
     consecutive
    0.08
    ØŃ
    0.07
    åıĬ以ä¸Ĭ
    0.07
    (!
    0.07
    ë²Ī
    0.07
    个
    0.07
    以ä¸ĬçļĦ
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
    Activations Density 0.329%

    No Known Activations