© 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. 39252
    Prev
    Next
    INDEX
    Explanations

    published by

    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
    lessly
    -0.10
    IBUT
    -0.09
    Å¡Äį
    -0.08
    ody
    -0.08
    .wikipedia
    -0.08
    ÙħÙĨد
    -0.08
    اء
    -0.08
    ãģ©ãĤĤ
    -0.08
    /from
    -0.08
    /null
    -0.08
    POSITIVE LOGITS
    (crate
    0.08
    ÙĨØ´
    0.07
    åĩºåİ»çļĦ
    0.07
    ä¸įåĩºåİ»
    0.07
    /print
    0.07
    åĩºåİ»
    0.07
    äº®çĽ¸
    0.07
    æį¢ä»£
    0.07
    ecchio
    0.07
    ICATION
    0.07
    Activations Density 0.130%

    No Known Activations