© 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. 51432
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    áºŃn
    -0.08
    illis
    -0.08
    ops
    -0.07
    ẬN
    -0.07
    estad
    -0.07
    lech
    -0.07
    æĺ¯ä¸Ģ缴
    -0.07
    drawing
    -0.07
    engg
    -0.07
    ellen
    -0.07
    POSITIVE LOGITS
    utus
    0.07
    ror
    0.07
    åĪĨæł¡
    0.07
    èĩ¼
    0.07
    uD
    0.07
    两çĶ¨
    0.07
    iori
    0.06
    theit
    0.06
    xBE
    0.06
    ç§Ģ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.