© 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. 63017
    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
    ebar
    -0.08
    ep
    -0.08
    èĮħ
    -0.07
    teria
    -0.07
    loe
    -0.07
    кÑĤо
    -0.07
    ä½łåĪ°åºķ
    -0.07
    ÙĬÙĪÙĨ
    -0.07
    ä¿¡
    -0.07
    åĽ½æ°ij
    -0.07
    POSITIVE LOGITS
    uesta
    0.09
     Lus
    0.07
    ï¸İ
    0.07
    ahnya
    0.07
    aszt
    0.07
    agni
    0.06
     Laurea
    0.06
    æĿIJæĸĻåıĬ
    0.06
    ä¾Ī
    0.06
    itaire
    0.06
    Activations Density 0.000%

    No Known Activations