© 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. 26111
    Prev
    Next
    INDEX
    Explanations

    mathematical, system, and chemical terms

    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
    2
    -0.08
    1
    -0.08
    -
    -0.08
    :
    -0.08
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    0
    -0.07
     is
    -0.06
     on
    -0.06
    3
    -0.06
    POSITIVE LOGITS
    ofday
    0.10
    ocache
    0.09
    ogos
    0.09
    -messages
    0.09
    -dat
    0.09
    ÃŃz
    0.09
    ')==
    0.09
     Ouver
    0.09
    istet
    0.09
    [section
    0.09
    Activations Density 0.012%

    No Known Activations