© 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. 61211
    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
    ÙĪرÙĥ
    -0.08
    çĦ¶æĺ¯
    -0.07
    ying
    -0.07
     pula
    -0.07
    amal
    -0.07
    æ´ĴèĦ±
    -0.06
    pul
    -0.06
    ol
    -0.06
    ellig
    -0.06
    å¾Ģå¾Ģæĺ¯
    -0.06
    POSITIVE LOGITS
    æĪijåIJ§
    0.08
    axe
    0.08
    felder
    0.07
     zami
    0.07
    ç²¾è¯ļ
    0.07
    æ¯Ĥ
    0.07
    æĪijäºĨ
    0.07
    allback
    0.07
    Carthy
    0.07
    ;set
    0.07
    Activations Density 0.000%

    No Known Activations