© 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. 65431
    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
    ugia
    -0.09
    è¿Ļå°±
    -0.08
    queo
    -0.07
    壮
    -0.07
    oled
    -0.07
    owo
    -0.07
    essus
    -0.07
    使æĪij
    -0.07
    åįļ大
    -0.07
    责任å¿ĥ强
    -0.07
    POSITIVE LOGITS
    aina
    0.07
    èĮħ
    0.07
    æķijæ²»
    0.06
    [:,:
    0.06
    请éĢīæĭ©
    0.06
    ãĤ³ãĥ¼ãĥ«
    0.06
     hail
    0.06
    å½ķçĶ¨
    0.06
    çľŁä¼ª
    0.06
    yl
    0.06
    Activations Density 0.000%

    No Known Activations