© 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. 24620
    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
    oto
    -0.07
    ogar
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
     Quer
    -0.07
    ...
    -0.07
    :index
    -0.06
    st
    -0.06
    uari
    -0.06
    æ²³æ±ł
    -0.06
    ÄĹl
    -0.06
    POSITIVE LOGITS
    edException
    0.09
    errick
    0.07
    -sign
    0.07
    sess
    0.07
    ESH
    0.07
    νοÏį
    0.07
    _none
    0.07
    plaintext
    0.07
    ä¸Ģè¡Į人
    0.07
    已累计
    0.07
    Activations Density 0.000%

    No Known Activations