© 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. 10911
    Prev
    Next
    INDEX
    Explanations

    punctuates lists or references

    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
    æģ°
    -0.07
    æĹ¢æľī
    -0.07
    æľīå¾ħ
    -0.06
    åį´ä¸įèĥ½
    -0.06
    erras
    -0.06
    unek
    -0.06
    Ãĸ
    -0.06
    ocker
    -0.06
    ingend
    -0.06
    stm
    -0.06
    POSITIVE LOGITS
    æĢ»ä¹ĭ
    0.09
    å§ĭç»Īä¿ĿæĮģ
    0.08
    esan
    0.08
    estu
    0.08
    å§ĭç»Ī以
    0.07
    lessly
    0.07
    iano
    0.07
    ä¸ĭåIJĮ
    0.07
    æĢ»èĢĮè¨Ģä¹ĭ
    0.07
     Swords
    0.07
    Activations Density 0.060%

    No Known Activations