© 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. 42954
    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
    碰åĪ°
    -0.08
     há»ķ
    -0.08
    éģĩåĪ°äºĨ
    -0.08
    اÙĪÙĨ
    -0.07
    amm
    -0.07
    ught
    -0.07
    碰
    -0.07
    aunch
    -0.07
    abra
    -0.06
    æĭ¿åĪ°äºĨ
    -0.06
    POSITIVE LOGITS
    åĪĩå®ŀåģļ好
    0.08
    ĥ
    0.08
    etag
    0.07
    robe
    0.07
    èĮ¨
    0.07
    ertian
    0.07
    zyn
    0.07
    åħ¹
    0.06
    armed
    0.06
    erox
    0.06
    Activations Density 0.000%

    No Known Activations