© 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. 64144
    Prev
    Next
    INDEX
    Explanations

    primary purpose of study

    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
    æĽ´ä¸įèĥ½
    -0.07
    abox
    -0.07
    æĽ´ä¸įæĺ¯
    -0.07
    æĽ´ä¸įä¼ļ
    -0.07
    æ¡¥åĮº
    -0.07
    .touch
    -0.07
    pmat
    -0.07
    parte
    -0.07
    æĽ´æ²¡æľī
    -0.07
    æĪij们没æľī
    -0.07
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.14
    åħ¶æ¬¡
    0.12
    以åıĬåħ¶ä»ĸ
    0.12
    è¾ħ以
    0.10
    为主
    0.10
    ãĤĴä¸Ńå¿ĥãģ«
    0.10
     supplemented
    0.10
     followed
    0.10
    为主çļĦ
    0.09
    ä½Ĩä¹Łæľī
    0.09
    Activations Density 0.886%

    No Known Activations