© 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. 61193
    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
    空æ°Ķæ¸ħæĸ°
    -0.07
    绣
    -0.07
    inol
    -0.07
    espo
    -0.07
    åĮħ头
    -0.06
    edo
    -0.06
     reap
    -0.06
    ධ
    -0.06
    -level
    -0.06
    λαι
    -0.06
    POSITIVE LOGITS
    ноÑģÑĤÑıми
    0.07
     OTHERWISE
    0.07
    ça
    0.07
    erar
    0.07
    oman
    0.07
     YYS
    0.07
     Klassen
    0.07
    ullet
    0.07
    {},
    0.07
    æĤ´
    0.07
    Activations Density 0.000%

    No Known Activations