© 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. 22220
    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
    è·»
    -0.09
    ТÐĴ
    -0.08
    åĴĸåķ¡åİħ
    -0.08
    TED
    -0.08
    æ²ĥæĸ¯
    -0.07
    ndx
    -0.07
    [to
    -0.07
    materi
    -0.07
    acias
    -0.07
    ruf
    -0.07
    POSITIVE LOGITS
    roll
    0.07
    ypes
    0.07
    æķı
    0.06
    ä¸įå¤ĸ
    0.06
    ichi
    0.06
    uson
    0.06
    asier
    0.06
    yta
    0.06
    -ever
    0.06
    .webkit
    0.06
    Activations Density 0.000%

    No Known Activations