© 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. 44100
    Prev
    Next
    INDEX
    Explanations

    image file extensions

    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
    ypi
    -0.07
    å¼ķ
    -0.07
    çĽĹ
    -0.07
    éļIJ
    -0.06
    亡
    -0.06
    è£
    -0.06
    æŁ¥
    -0.06
    æ®Ĭ
    -0.06
    ä¸įåIJĮäºİ
    -0.06
    çĻ¾åIJĪ
    -0.06
    POSITIVE LOGITS
    .jpg
    0.09
    roe
    0.09
    .pdf
    0.08
    _-_
    0.08
     implanta
    0.08
    \",\"
    0.08
     undermin
    0.08
    .xlsx
    0.08
    _proof
    0.07
    _final
    0.07
    Activations Density 0.308%

    No Known Activations