© 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. 65057
    Prev
    Next
    INDEX
    Explanations

    source file or code

    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
    ìĤ¬íķŃ
    -0.09
    jenigen
    -0.09
     ìĤ¬íķŃ
    -0.09
    raries
    -0.09
    à¹ĭ
    -0.08
    ernel
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    umente
    -0.07
    /LICENSE
    -0.07
    á»ĩn
    -0.07
    POSITIVE LOGITS
    hood
    0.11
    less
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ر
    0.09
    er
    0.08
    ä¸įæĺİçļĦ
    0.08
    ipt
    0.08
    ivity
    0.08
    ages
    0.08
    forge
    0.08
    Activations Density 0.074%

    No Known Activations