© 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. 17646
    Prev
    Next
    INDEX
    Explanations

    figuring it out

    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
    åħ¶ä¸º
    -0.07
    åıĬåħ¶
    -0.07
    ä¹ĭ称
    -0.07
    çļĦåIJĹ
    -0.07
    å°Ĩåħ¶
    -0.07
    ä¸ĭåIJĮ
    -0.06
    ly
    -0.06
    ä¹ĭ
    -0.06
     whose
    -0.06
    agogue
    -0.06
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.07
     ngh
    0.07
    ogar
    0.07
    ulang
    0.07
    èĦijåIJİ
    0.07
    :
    0.07
    tav
    0.07
    зовой
    0.07
    èĩ´çļĦ
    0.07
    :^
    0.07
    Activations Density 0.028%

    No Known Activations