© 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. 25535
    Prev
    Next
    INDEX
    Explanations

    presenting *as*

    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
    ords
    -0.09
    jak
    -0.08
    ecraft
    -0.08
    hipster
    -0.08
    ultas
    -0.08
    plorer
    -0.08
    ÑĢей
    -0.08
    ffre
    -0.08
    éĩįè¦ģæĮĩ示
    -0.08
    èģĮå®Ī
    -0.08
    POSITIVE LOGITS
     вниманиÑİ
    0.09
     forth
    0.08
    Äı
    0.08
     Ñģобой
    0.07
    /view
    0.07
     bÃły
    0.07
    çļĦæĺ¯ä¸Ģ个
    0.07
    à¹ģà¸Ļะ
    0.07
    weise
    0.07
    å®Įæķ´çļĦ
    0.07
    Activations Density 0.074%

    No Known Activations