© 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. 23489
    Prev
    Next
    INDEX
    Explanations

    other languages or forms of "other"

    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
    æľīä¸Ģ段
    -0.07
    ابÙĩ
    -0.07
    ame
    -0.07
    åģĩå®ļ
    -0.07
    åıĪå¤ļ
    -0.06
    ucin
    -0.06
    itsu
    -0.06
    æľīä¸Ģ份
    -0.06
    åĩºæĸ°
    -0.06
    æĪijæľĢåĸľæ¬¢
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.12
    çļĦåħ¶ä»ĸ
    0.12
    对åħ¶ä»ĸ
    0.11
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.10
     otras
    0.10
     otros
    0.10
     other
    0.10
    ä»ĸãģ®
    0.10
     autres
    0.10
    other
    0.10
    Activations Density 0.003%

    No Known Activations