© 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. 43189
    Prev
    Next
    INDEX
    Explanations

    comparisons and qualifiers (like mere, besides, beyond)

    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
    scp
    -0.08
    缸åºĶ
    -0.08
    计ç®Ĺæľºè½¯ä»¶
    -0.08
    iern
    -0.07
    ä»Ĭ度ãģ¯
    -0.07
    azel
    -0.07
    ÏĢα
    -0.07
    omm
    -0.07
    ells
    -0.07
     swe
    -0.07
    POSITIVE LOGITS
    åįķ纯çļĦ
    0.10
     mere
    0.10
     merely
    0.08
    åįķ纯
    0.08
     Ùħجرد
    0.08
     sekedar
    0.08
     sekadar
    0.07
     pure
    0.07
    ccio
    0.07
    Fcn
    0.07
    Activations Density 0.110%

    No Known Activations