© 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. 45031
    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
    yped
    -0.08
    epe
    -0.08
     vÃłnh
    -0.08
     hors
    -0.08
    olÃŃ
    -0.08
    Õ¡Õ®
    -0.08
    verso
    -0.07
    øv
    -0.07
    身ä¸Ĭä¸ĭ
    -0.07
    brero
    -0.07
    POSITIVE LOGITS
    åı¯èĥ½æĢ§
    0.07
    annes
    0.07
    urg
    0.07
     ease
    0.07
     Woo
    0.06
    çļĦåı¯èĥ½æĢ§
    0.06
    ç¬ij
    0.06
    (crate
    0.06
     lim
    0.06
    s
    0.06
    Activations Density 0.000%

    No Known Activations