© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61930
    Prev
    Next
    INDEX
    Explanations

    convert X into Y

    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
    åįģæĹ¥åĨħ
    -0.08
    éŃĶ鬼
    -0.08
    ä¸įçŁ¥éģĵèĩªå·±
    -0.08
    utti
    -0.08
    occhi
    -0.08
    óc
    -0.08
    æ£ĢæŁ¥ç»Ħ
    -0.08
    åħ¨éĿ¢äºĨ解
    -0.08
    åħ¨ç³»
    -0.08
    åħ§å¤ĸ
    -0.08
    POSITIVE LOGITS
    convert
    0.13
     converting
    0.12
    转æį¢æĪIJ
    0.11
     conversion
    0.11
     convert
    0.11
    转åĮĸæĪIJ
    0.11
     convertible
    0.11
     Convert
    0.11
    转åĮĸ为
    0.11
     converted
    0.10
    Activations Density 0.072%

    No Known Activations