© 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. 42096
    Prev
    Next
    INDEX
    Explanations

    clinically relevant magnitude of effects

    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
    iaux
    -0.08
    usso
    -0.08
    ç±²
    -0.08
    ystation
    -0.07
    为空
    -0.07
    eced
    -0.07
     ngặt
    -0.07
     emptied
    -0.07
    usta
    -0.07
    ä¾ĽåºĶä¿¡æģ¯
    -0.07
    POSITIVE LOGITS
     magnitude
    0.09
    å¹ħ度
    0.09
    Magnitude
    0.08
     meaningful
    0.08
    magnitude
    0.08
    å¤ļ大çļĦ
    0.07
    æľīå¤ļ大
    0.07
    .margin
    0.07
    åĬĽåº¦
    0.07
     clinically
    0.07
    Activations Density 0.023%

    No Known Activations