© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61879
    Prev
    Next
    INDEX
    Explanations

    without

    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
    uite
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
    иа
    -0.06
    arra
    -0.06
     ctypes
    -0.06
    æľ¬ç¯ĩæĸĩç«ł
    -0.06
    aning
    -0.06
    è··
    -0.06
    _cls
    -0.06
    æĹłè¯¯
    -0.06
    POSITIVE LOGITS
     anymore
    0.10
    å¼ķ
    0.09
    æĪĸå°ij
    0.09
    ç²¾çĽĬæ±Ĥç²¾
    0.08
    çĽ²çĽ®
    0.08
     redundant
    0.08
    rovers
    0.08
    å¤ļä½ĻçļĦ
    0.07
    ä»»ä½ķ
    0.07
    å¤ļä½Ļ
    0.07
    Activations Density 0.077%

    No Known Activations