© 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. 34191
    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
    没说
    -0.07
    ebu
    -0.06
    oven
    -0.06
    çĻ¾èįī
    -0.06
     cach
    -0.06
    没
    -0.06
    éros
    -0.06
    awal
    -0.06
    éĻ£
    -0.06
    edio
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥ç»§ç»Ń
    0.08
    perse
    0.08
    è¿İéļ¾èĢĮä¸Ĭ
    0.08
    èĢĮ代ä¹ĭ
    0.08
    çļĦæ²»çĸĹæĸ¹æ³ķ
    0.07
     exploration
    0.07
    asy
    0.07
    alsa
    0.07
    attr
    0.07
    æł¼æł¼
    0.07
    Activations Density 0.000%

    No Known Activations