© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26823
    Prev
    Next
    INDEX
    Explanations

    contrast and comparison

    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
    ambre
    -0.07
    WindowTitle
    -0.07
    çŀ»
    -0.06
    ns
    -0.06
    ç¥Ŀç¦ıä½ł
    -0.06
    åĬŀäºĭ
    -0.06
    xb
    -0.06
    .tick
    -0.06
    LS
    -0.06
    ebi
    -0.06
    POSITIVE LOGITS
    对æ¯Ķ
    0.10
     contrast
    0.09
     {*}
    0.08
     comparison
    0.08
    对çħ§
    0.08
    å¸ļ
    0.07
    å°įæ¯Ķ
    0.07
     Contrast
    0.07
    åıįä¹īè¯į
    0.07
     contrasting
    0.07
    Activations Density 0.096%

    No Known Activations