© 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. 18763
    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
    ä¸Ģå¤ķ
    -0.09
     beho
    -0.08
    obie
    -0.08
    åĬªåĬĽæĬĬ
    -0.08
    nTo
    -0.08
    رÙĨ
    -0.08
    ervas
    -0.08
    ToEnd
    -0.08
    αιο
    -0.07
    ä½ĵèĤ²åѦéĻ¢
    -0.07
    POSITIVE LOGITS
    esses
    0.07
    åı¯ä¸įæĺ¯
    0.06
    è¿Ļ个
    0.06
    æĵ¦
    0.06
    çħ§
    0.06
    ajak
    0.06
     mental
    0.06
    mentation
    0.06
    Âł
    0.06
    åķ¬
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.