© 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. 13154
    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
    jaht
    -0.08
    Ñģами
    -0.08
    anya
    -0.07
    agnes
    -0.07
    æ´²
    -0.07
    Ñģом
    -0.07
    aña
    -0.07
    ία
    -0.07
    ä¸İåIJ¦
    -0.07
    âĢ¦the
    -0.07
    POSITIVE LOGITS
    鸳鸯
    0.08
    zi
    0.06
    _repr
    0.06
    好ä¸į
    0.06
    ç»ĵ论
    0.06
    æĸ¹éĺµ
    0.06
    Ïĥί
    0.06
    çĸ¯
    0.06
     Rent
    0.06
    _managed
    0.06
    Activations Density 0.000%

    No Known Activations