© 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. 49735
    Prev
    Next
    INDEX
    Explanations

    Yii framework 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
    erto
    -0.07
    rie
    -0.06
    tin
    -0.06
    ä¸Ģèµ·æĿ¥çľĭçľĭåIJ§
    -0.06
    erta
    -0.06
    ãģ®ãĤĤãģ®
    -0.06
    说æĺ¯
    -0.06
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.06
    way
    -0.06
    ée
    -0.06
    POSITIVE LOGITS
    hopefully
    0.09
    oppen
    0.08
    iona
    0.08
    گرد
    0.08
    è½¼
    0.08
    áĢĬ
    0.07
    ×Ĺ׳×ķ
    0.07
    å¿ĥæľī
    0.07
    没æľīäºĨ
    0.07
    ÐŁÐļ
    0.07
    Activations Density 0.026%

    No Known Activations