© 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. 41168
    Prev
    Next
    INDEX
    Explanations

    leaving

    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
    лед
    -0.07
    lö
    -0.07
    ä¸įæĭĶ
    -0.07
    avanaugh
    -0.07
     Dewi
    -0.06
    è¡Įäºĭ
    -0.06
     Hinblick
    -0.06
     suicides
    -0.06
     пÑĢоезда
    -0.06
    ousel
    -0.06
    POSITIVE LOGITS
     hẳn
    0.09
    æŃ£è½¨
    0.08
     khá»ıi
    0.08
    گز
    0.08
    bane
    0.08
    ure
    0.08
    rosse
    0.07
    roc
    0.07
    heen
    0.07
    à¤Łà¤¨à¤¾
    0.07
    Activations Density 0.039%

    No Known Activations