© 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. 17319
    Prev
    Next
    INDEX
    Explanations

    instead

    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
    mares
    -0.09
    pth
    -0.08
    idet
    -0.07
    Marsh
    -0.07
    Bron
    -0.07
    Įĵ
    -0.07
    atives
    -0.07
     à¹Ĥล
    -0.07
     puff
    -0.07
    Rez
    -0.07
    POSITIVE LOGITS
    èĻ½çĦ¶ä¸įæĺ¯
    0.10
    åħ¶å®ŀæĺ¯
    0.09
    å®ŀéĻħä¸Ĭæĺ¯
    0.08
    ymp
    0.08
    åıĺ缸
    0.08
    åħ¶å®ŀ
    0.08
     instead
    0.08
    erah
    0.08
    instead
    0.08
    æł¹æľ¬ä¸įæĺ¯
    0.07
    Activations Density 0.143%

    No Known Activations