© 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. 28964
    Prev
    Next
    INDEX
    Explanations

    purification and separation

    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
    Setter
    -0.07
    urch
    -0.07
    å¢
    -0.07
    æĽ¿è¡¥
    -0.07
    ignon
    -0.07
     Attack
    -0.07
    æĹłå¿Į
    -0.07
    ä¸į设
    -0.07
    åħ¨åĭ¤
    -0.07
     mãn
    -0.07
    POSITIVE LOGITS
    åĪĨ离
    0.15
     separation
    0.15
     separating
    0.14
     separ
    0.13
    纯åĮĸ
    0.13
     separates
    0.13
     Separ
    0.12
    -separated
    0.12
     tách
    0.12
    Separ
    0.12
    Activations Density 0.146%

    No Known Activations