© 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. 30667
    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
    éļĽ
    -0.08
    æĿ¥äºº
    -0.07
    å·¥ä½ľåıĬ
    -0.07
    ôt
    -0.07
    ä¼°
    -0.07
    kus
    -0.07
    è¿ĶãģĹ
    -0.07
    ainer
    -0.06
    _si
    -0.06
    æĹłèĻij
    -0.06
    POSITIVE LOGITS
    çļĦåħ·ä½ĵæĥħåĨµ
    0.07
    piegel
    0.06
    phabet
    0.06
    odem
    0.06
    ä¸İåİŁ
    0.06
    idente
    0.06
    åħ·ä½ĵæĥħåĨµ
    0.06
    è¿Ľè¡ĮæŶ
    0.06
    modification
    0.06
    夷
    0.06
    Activations Density 0.000%

    No Known Activations