© 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. 11684
    Prev
    Next
    INDEX
    Explanations

    bandwidth or width

    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
    igli
    -0.07
    zsche
    -0.07
     ánimo
    -0.07
    attet
    -0.07
    æŶæľīåıijçĶŁ
    -0.07
    uco
    -0.07
     seco
    -0.06
    istically
    -0.06
    .bc
    -0.06
    çıŃåĪĹ
    -0.06
    POSITIVE LOGITS
    width
    0.10
     bandwidth
    0.09
    宽度
    0.08
    çªĦ
    0.07
     hẹp
    0.07
    range
    0.07
    éļĻ
    0.07
    (IT
    0.07
    ned
    0.07
    ewidth
    0.07
    Activations Density 0.009%

    No Known Activations