© 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. 8432
    Prev
    Next
    INDEX
    Explanations

    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
    å°ijåħĪ
    -0.08
    ibd
    -0.07
    ä¸įåħį
    -0.07
    iew
    -0.06
    ieno
    -0.06
    ä¸įå®ļ
    -0.06
    ä¸īçĶŁ
    -0.06
    å·¥ä½ľæĸ¹å¼ı
    -0.06
    .hit
    -0.06
    ä»Ĭ天è¦ģ
    -0.06
    POSITIVE LOGITS
     separation
    0.13
     separating
    0.12
    è¿ľç¦»
    0.11
     Separ
    0.11
    离
    0.10
     separates
    0.10
    éļĶ离
    0.10
    åĪĨ离
    0.10
    éļĶéĽ¢
    0.10
    éģłéĽ¢
    0.10
    Activations Density 0.012%

    No Known Activations