© 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. 25913
    Prev
    Next
    INDEX
    Explanations

    Dipartimento, ique, Est, Tij

    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
    ablish
    -0.08
    adier
    -0.08
    rowse
    -0.07
    ÅĽni
    -0.07
    -0.07
    鼶åħ«
    -0.07
    :init
    -0.07
    odaw
    -0.07
     <<-
    -0.07
    -Headers
    -0.07
    POSITIVE LOGITS
    æģ©
    0.08
    /en
    0.07
    èĤ¢
    0.06
    _en
    0.06
    åı°ä¸ĭ
    0.06
    BC
    0.06
    enz
    0.06
    En
    0.06
    沫
    0.06
    è¿Ī
    0.06
    Activations Density 0.060%

    No Known Activations