© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21859
    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
    æķ·
    -0.07
    -bind
    -0.07
     Bum
    -0.07
    æľ¬çīĪ
    -0.06
    LING
    -0.06
    yser
    -0.06
    çĸĹ
    -0.06
    anh
    -0.06
    лоÑĤ
    -0.06
    neys
    -0.06
    POSITIVE LOGITS
    è¾
    0.08
    adius
    0.07
    oviÄĩ
    0.07
    åĨħ容çĶ±
    0.07
     intra
    0.07
    दि
    0.07
     غض
    0.07
    åºŃ
    0.07
    åį³ä»¥
    0.07
    æĸ¹ä½į
    0.07
    Activations Density 0.000%

    No Known Activations