© 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. 61284
    Prev
    Next
    INDEX
    Explanations

    emulsification or foam rolling

    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
    pris
    -0.08
    chè
    -0.07
    ãĥ«ãĤ¯
    -0.07
    ç§įç§įåİŁåĽł
    -0.07
    falls
    -0.07
    å®īæİĴçļĦ
    -0.06
    pek
    -0.06
    ãģĸãģ¾
    -0.06
    eken
    -0.06
    ##_
    -0.06
    POSITIVE LOGITS
    çĬ¶
    0.09
    ulent
    0.09
    çļĦå½¢æĪIJ
    0.09
    çĬ¶çļĦ
    0.09
    ier
    0.09
    ulant
    0.08
    åīĤåĴĮ
    0.08
    æĸ°çĶŁæ´»
    0.08
    çĭĢ
    0.08
    Ùİاء
    0.08
    Activations Density 0.042%

    No Known Activations