© 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. 56440
    Prev
    Next
    INDEX
    Explanations

    sequence 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
    æĺ¯ä¸ĢåĪĩ
    -0.06
    æĻ¨æĬ¥
    -0.06
    éĽıå½¢
    -0.06
    ëij
    -0.06
    å½ĵ头
    -0.06
     calculation
    -0.06
    ä»ħ次äºİ
    -0.06
    깨
    -0.06
    dor
    -0.06
    xmlns
    -0.06
    POSITIVE LOGITS
     conver
    0.10
     converged
    0.10
     converge
    0.09
    åºıåĪĹ
    0.09
     sequence
    0.08
    ä¸įæĸŃè¿ĽæŃ¥
    0.08
    åħ´
    0.08
     Conver
    0.08
    ä¸ĢéĺŁ
    0.08
    serie
    0.08
    Activations Density 0.012%

    No Known Activations