© 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. 28376
    Prev
    Next
    INDEX
    Explanations

    intersecting

    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
    ward
    -0.09
     tuá»ķi
    -0.08
    ä½łæĺ¯è°ģ
    -0.08
    wards
    -0.08
    zada
    -0.08
    hattan
    -0.08
     serialVersionUID
    -0.08
    WARDS
    -0.07
    rouch
    -0.07
    æĢİä¹Īèµ°
    -0.07
    POSITIVE LOGITS
    ing
    0.13
    eenth
    0.09
    ively
    0.08
    åľ¨
    0.08
    ศ
    0.08
    ible
    0.07
    ÙĨÛĮ
    0.07
    ed
    0.07
    ibly
    0.07
     nhau
    0.07
    Activations Density 0.004%

    No Known Activations