© 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. 28968
    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¶ĬåĨ¬
    -0.07
    uther
    -0.07
    å¤ļä¹Ī
    -0.06
    menta
    -0.06
    kc
    -0.06
    rano
    -0.06
    iegel
    -0.06
    cka
    -0.06
    æľīéĤ£ä¹Ī
    -0.06
    _estimate
    -0.06
    POSITIVE LOGITS
    _CHARSET
    0.09
    Å¡Äį
    0.08
    Õ½
    0.08
    bem
    0.07
    uty
    0.07
    braska
    0.07
    Ïģη
    0.07
    äºĨçľ¼
    0.07
    Spacing
    0.07
    SourceType
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.