© 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. 55773
    Prev
    Next
    INDEX
    Explanations

    composing strings and media

    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
    ÙĪص
    -0.08
    ÑĪÑĤа
    -0.08
    ä¸Ģ个åı«
    -0.08
     ritor
    -0.07
    åĴĮ建设
    -0.07
    å³¥åµĺ
    -0.07
    ož
    -0.07
     wandering
    -0.07
    owa
    -0.07
    глÑı
    -0.07
    POSITIVE LOGITS
     consisting
    0.10
     composed
    0.09
     consists
    0.08
     consist
    0.08
     terdiri
    0.08
     consisted
    0.08
     comprised
    0.08
    ä¾£
    0.07
    å®Įæķ´
    0.07
    dress
    0.07
    Activations Density 0.275%

    No Known Activations