© 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. 15283
    Prev
    Next
    INDEX
    Explanations

    relationships, insult, new, food

    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
    两çĶ¨
    -0.07
    ä¹ĭåĪĹ
    -0.06
    èĽ¹
    -0.06
    ä¸įèĪį
    -0.06
    à¸ŀัà¸ģ
    -0.06
     either
    -0.06
    o
    -0.06
    ula
    -0.06
    ä¹ĥèĩ³
    -0.06
     whatever
    -0.06
    POSITIVE LOGITS
    大åħ¸
    0.08
    hias
    0.08
    empi
    0.07
    undra
    0.07
    ä¿±è¿Ľ
    0.07
    å°±æĺ¯æľĢ好çļĦ
    0.07
    æľīäºĨæĸ°çļĦ
    0.07
    :NO
    0.07
    大åħ¨
    0.07
    *sp
    0.07
    Activations Density 0.001%

    No Known Activations