© 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. 2612
    Prev
    Next
    INDEX
    Explanations

    contrast or contrasting

    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
    mp
    -0.06
     vi
    -0.06
    _ignore
    -0.06
    å®ĥéĤ£
    -0.06
     application
    -0.05
    ä¸ºæł¸å¿ĥ
    -0.05
     br
    -0.05
    olem
    -0.05
     tr
    -0.05
    Live
    -0.05
    POSITIVE LOGITS
    对æ¯Ķ
    0.12
    å°įæ¯Ķ
    0.10
    缸æ¯Ķä¹ĭä¸ĭ
    0.10
     contrasting
    0.09
     contrast
    0.08
     contraste
    0.08
     ë¹Ħíķ´
    0.08
    лиÑģ
    0.08
    èĩªæĿ¥
    0.08
    åıįè§Ĥ
    0.08
    Activations Density 0.114%

    No Known Activations