© 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. 24389
    Prev
    Next
    INDEX
    Explanations

    convert, conversion, converting

    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
    æĪĴçĥŁ
    -0.08
    acer
    -0.08
    Ĥ¹
    -0.08
     assoluto
    -0.08
    OLL
    -0.08
    .gradle
    -0.07
    çĥŁéħĴ
    -0.07
    AGMA
    -0.07
    èĩªè¾¾
    -0.07
    å¼Ģ好
    -0.07
    POSITIVE LOGITS
     convert
    0.10
     converting
    0.09
     conversion
    0.09
     conversions
    0.09
     converts
    0.09
    转æį¢ä¸º
    0.08
     Converts
    0.08
    convert
    0.08
    Conversion
    0.08
    _conversion
    0.08
    Activations Density 0.009%

    No Known Activations