© 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. 27587
    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
    åĢĴåľ¨
    -0.07
    ÙħاÙĦ
    -0.07
    odie
    -0.07
    ạo
    -0.07
    xing
    -0.06
    ä»ĭ
    -0.06
    åĩ«
    -0.06
     sense
    -0.06
    ä¾ĭ
    -0.06
    çļ
    -0.06
    POSITIVE LOGITS
    onnier
    0.08
     Pret
    0.08
    apar
    0.07
    ache
    0.07
    ëįĶëĭĪ
    0.07
    edriver
    0.07
    éķ¿èĻ¹
    0.07
    ItemClick
    0.07
    üng
    0.07
    æį¢æīĭ
    0.07
    Activations Density 0.000%

    No Known Activations