© 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. 61383
    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
    kina
    -0.09
    çļĦ大好
    -0.08
    èĩªè§īéģµå®Ī
    -0.07
    æħ¨
    -0.07
    uno
    -0.07
    imson
    -0.07
    à¸Ľà¸£à¸°à¸ģ
    -0.07
    asila
    -0.07
    angguan
    -0.07
     permalink
    -0.07
    POSITIVE LOGITS
    å¤ĩ
    0.07
    éĢł
    0.06
    imple
    0.06
    صÙģ
    0.06
    å°ģ
    0.06
    (sync
    0.06
    ä¸į讲
    0.06
    Returned
    0.06
    ä¸Ĭéĺµ
    0.06
    ÑĢÑĥÑĤ
    0.06
    Activations Density 0.000%

    No Known Activations