© 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. 32856
    Prev
    Next
    INDEX
    Explanations

    distillation and distilled water

    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
    ëŀŃ
    -0.10
    æĦıçļĦ
    -0.09
    FUL
    -0.09
    dsl
    -0.09
    åĵ½
    -0.08
    ÃŃv
    -0.08
    zte
    -0.08
    DSL
    -0.08
    /********************************************************************************
    -0.08
    ืà¸Ļ
    -0.08
    POSITIVE LOGITS
    åĪĨ离
    0.08
     separates
    0.08
     separation
    0.08
     separating
    0.07
    illation
    0.07
     ulang
    0.07
    åĪĨéĽ¢
    0.06
    ughter
    0.06
     separ
    0.06
    åĩºæĿ¥çļĦ
    0.06
    Activations Density 0.004%

    No Known Activations