© 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. 10166
    Prev
    Next
    INDEX
    Explanations

    between different things

    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
    jenigen
    -0.13
    اÙĭ
    -0.10
    mente
    -0.09
    spell
    -0.09
    lement
    -0.08
    apkan
    -0.08
    fully
    -0.08
    warzys
    -0.08
    zioni
    -0.08
    iscal
    -0.08
    POSITIVE LOGITS
    i
    0.12
    ÙĬ
    0.09
    и
    0.09
    ãĥ¼
    0.09
    sver
    0.09
    ×Ļ
    0.09
    à¥Ģ
    0.09
    /on
    0.09
    à§ĩ
    0.08
    ãĤĬ
    0.08
    Activations Density 0.023%

    No Known Activations