© 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. 24033
    Prev
    Next
    INDEX
    Explanations

    inventor actions

    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
    ÙĥÙĬ
    -0.07
     Stéph
    -0.07
    è¿ĺæĺ¯éĿŀ常
    -0.07
    ä¸Ĭåı£
    -0.07
    geois
    -0.07
    wai
    -0.07
    ä¸įå¦Ĥ
    -0.06
    ä¸ĢçĤ¹éĥ½ä¸į
    -0.06
    é¹ĥ
    -0.06
    ä¸įæĶ¾
    -0.06
    POSITIVE LOGITS
    éĤ£å°±æĺ¯
    0.12
     bernama
    0.12
    åIJįåŃĹåı«
    0.12
     namens
    0.11
    à¸Ĭืà¹Īà¸Ńวà¹Īา
    0.11
    å®ĥå°±æĺ¯
    0.10
    åIJįåı«
    0.10
    åı«åģļ
    0.10
    åı«ä»Ģä¹Ī
    0.10
    åIJį为
    0.10
    Activations Density 0.401%

    No Known Activations