© 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. 24038
    Prev
    Next
    INDEX
    Explanations

    spleen, ovary, ectomy

    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
    æĹłå¿Į
    -0.08
    èĪĮå°ĸ
    -0.08
    iles
    -0.08
    ç«¿
    -0.07
    æ·³
    -0.07
    å°ı康
    -0.07
    æĦĪæ¼ĶæĦĪ
    -0.07
    å±ģ
    -0.07
    kaar
    -0.07
    -uppercase
    -0.07
    POSITIVE LOGITS
     hil
    0.08
     gland
    0.08
    ectomy
    0.08
    วาย
    0.08
    èĤ¿å¤§
    0.08
    å½¢çĬ¶
    0.08
    åĪĩéĻ¤æľ¯
    0.08
     모ìĸij
    0.07
    éĻħ
    0.07
    wort
    0.07
    Activations Density 0.136%

    No Known Activations