© 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. 51288
    Prev
    Next
    INDEX
    Explanations

    to execution or disabling

    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
    ä¸įäºĨ解
    -0.08
    комплек
    -0.08
    æľī空
    -0.08
    éĹ²
    -0.07
    çµ®
    -0.07
    éĸij
    -0.07
    idler
    -0.07
    ä¸Ģ人
    -0.06
    pek
    -0.06
    axon
    -0.06
    POSITIVE LOGITS
    æł¹æľ¬ä¸į
    0.11
    å®Įåħ¨æ²¡æľī
    0.09
    å°½éĩıéģ¿åħį
    0.09
    æł¹æľ¬å°±æ²¡æľī
    0.09
    æł¹æľ¬æ²¡æľī
    0.09
    å®Įåħ¨ä¸į
    0.09
    æł¹æľ¬
    0.09
    ilu
    0.09
    æł¹æľ¬å°±ä¸į
    0.08
    LU
    0.08
    Activations Density 0.295%

    No Known Activations