© 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. 17674
    Prev
    Next
    INDEX
    Explanations

    (author, year) citations

    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
    umo
    -0.09
    à¤¿à¤Ł
    -0.08
    ãģ¹ãģ¦
    -0.08
    ional
    -0.08
    ness
    -0.07
    ident
    -0.07
    abb
    -0.07
    eldorf
    -0.07
    repid
    -0.07
    EAU
    -0.07
    POSITIVE LOGITS
    lessly
    0.08
    úa
    0.08
    esion
    0.08
    astia
    0.08
    hood
    0.08
    atorial
    0.07
    inian
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ornings
    0.07
    ctrine
    0.07
    Activations Density 0.587%

    No Known Activations