© 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. 46944
    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
    yiz
    -0.07
    æĬ¢
    -0.07
    imus
    -0.07
    Ñħоз
    -0.07
    azzi
    -0.06
    ä¸Ģ次次
    -0.06
    träger
    -0.06
    prob
    -0.06
    ä¸Ģ次åıĪä¸Ģ次
    -0.06
    åľ¨ä¸ľ
    -0.06
    POSITIVE LOGITS
    设å¤ĩåĪ¶éĢł
    0.08
    oko
    0.07
    {_
    0.07
    etsk
    0.07
    .Serve
    0.07
    èµ·æĿ¥åIJ§
    0.07
    ıc
    0.07
     Karr
    0.07
     Fauc
    0.07
    éľĵ
    0.07
    Activations Density 0.000%

    No Known Activations