© 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. 25910
    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
    ogenerated
    -0.08
    ого
    -0.08
    uxtap
    -0.08
    á»ĩu
    -0.08
    tahl
    -0.08
    uetype
    -0.07
    ам
    -0.07
    omic
    -0.07
    çļĦ认åı¯
    -0.07
    toral
    -0.07
    POSITIVE LOGITS
    ly
    0.13
    æĹłè¯¯
    0.12
    ely
    0.10
    íŀĪ
    0.10
    à¸Ĭัà¸Ķ
    0.09
    heiten
    0.09
    åľ°å°Ĩ
    0.09
     rÃłng
    0.09
    -ish
    0.08
     rằng
    0.08
    Activations Density 0.000%

    No Known Activations