© 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. 55413
    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
    aren
    -0.07
    ä¸ĵéŨ
    -0.07
    ä¸ĵéŨçļĦ
    -0.07
    é£İéľľ
    -0.07
    oug
    -0.06
    reo
    -0.06
     تÙħاÙħÙĭا
    -0.06
     dedicated
    -0.06
    æĭ£
    -0.06
    assar
    -0.06
    POSITIVE LOGITS
    eload
    0.08
    ä¸ĢæĪ·
    0.08
    å°ıçĻ½
    0.08
    imah
    0.08
    å°ıéĩij
    0.08
    碧
    0.07
    евиÑĩ
    0.07
    weep
    0.07
    iena
    0.07
    attet
    0.07
    Activations Density 0.000%

    No Known Activations