© 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. 60629
    Prev
    Next
    INDEX
    Explanations

    if, when, conditions

    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
    rafa
    -0.08
    è·¯æĺĵæĸ¯
    -0.07
     Manh
    -0.07
    Bundle
    -0.07
    éĴ¦
    -0.07
    loat
    -0.07
    оÑĩе
    -0.07
     sheer
    -0.07
    ectos
    -0.07
    롯
    -0.07
    POSITIVE LOGITS
     hypoth
    0.10
    /if
    0.09
     conditions
    0.09
     شرط
    0.09
    æĿ¡ä»¶åĴĮ
    0.09
     premises
    0.09
     hypothetical
    0.08
    æĿ¡ä»¶
    0.08
    conditions
    0.08
     premise
    0.08
    Activations Density 0.006%

    No Known Activations