© 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. 55440
    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
    details
    -0.07
    perm
    -0.07
    года
    -0.07
    baus
    -0.07
    detail
    -0.07
    约æĿŁ
    -0.06
    кÑĥÑĢ
    -0.06
    -detail
    -0.06
    ÑĤей
    -0.06
     Stär
    -0.06
    POSITIVE LOGITS
    esco
    0.08
    ecto
    0.08
    ä¸Ģå¤ķ
    0.07
     Huff
    0.07
    agne
    0.07
    udd
    0.07
     chou
    0.07
    ëĭ¥
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    Uid
    0.07
    Activations Density 0.000%

    No Known Activations