© 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. 64387
    Prev
    Next
    INDEX
    Explanations

    sequences and convergence

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    лиÑĨ
    -0.08
     оÑĤо
    -0.08
     offsetof
    -0.08
    ä¸½å¨ľ
    -0.07
    æ¯Ķä¾ĭçļĦ
    -0.07
    å°Ķé¡¿
    -0.07
    ures
    -0.07
    第ä¸ĢæŶéĹ´
    -0.07
     Seam
    -0.07
    :expr
    -0.07
    POSITIVE LOGITS
    éĢ¼è¿ij
    0.08
    æĶ¶æķĽ
    0.08
     monot
    0.08
     converge
    0.08
     convergence
    0.07
    ä¸Ķæľī
    0.07
     bounded
    0.07
     bounding
    0.07
     conver
    0.07
    è¶ĭäºİ
    0.07
    Activations Density 0.004%

    No Known Activations