© 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. 49011
    Prev
    Next
    INDEX
    Explanations

    conjunctions like but

    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
    everything
    -0.07
     Kasino
    -0.07
    делÑĭ
    -0.07
    ä¸Ģèĩ´è®¤ä¸º
    -0.07
     =========================================================================
    -0.06
    æĹłçĸijæĺ¯
    -0.06
    å¸ĥ伦
    -0.06
    —to
    -0.06
    alled
    -0.06
    .news
    -0.06
    POSITIVE LOGITS
     but
    0.20
    but
    0.18
    ,but
    0.18
    ä½Ĩ
    0.18
     But
    0.18
    ä½Ĩåľ¨
    0.17
    But
    0.17
     aber
    0.17
    ä½ĨæĪij们
    0.17
    ä½Ĩ对äºİ
    0.17
    Activations Density 0.073%

    No Known Activations