© 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. 21524
    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
     McK
    -0.08
    åįķçļĦ
    -0.08
     ordered
    -0.07
    ynchronously
    -0.07
     Ordered
    -0.07
    å°Ķå¤ļ
    -0.07
    çļĦåĭĩæ°Ķ
    -0.06
    \C
    -0.06
    强åĬĽ
    -0.06
    娴
    -0.06
    POSITIVE LOGITS
    bard
    0.08
    beat
    0.08
    -dismiss
    0.07
    仲
    0.07
    okal
    0.07
    ngle
    0.07
    åµ
    0.07
    unci
    0.07
    oust
    0.07
     angst
    0.07
    Activations Density 0.000%

    No Known Activations