© 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. 22813
    Prev
    Next
    INDEX
    Explanations

    "is the behaviour"

    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
    æīįå¾Ĺ以
    -0.06
    ostas
    -0.06
    è¿Ļ使å¾Ĺ
    -0.06
    å°±åĽłä¸º
    -0.06
     Completely
    -0.06
    inds
    -0.06
    åĪĨéħįåĪ°
    -0.06
    æ¯ıä¸ĢåIJį
    -0.06
    åĨįä¸Ģ次
    -0.06
    è¿Ľä¸ĢæŃ¥åĬłå¼º
    -0.06
    POSITIVE LOGITS
     yourself
    0.10
    并注æĦı
    0.10
    ä½łèº«è¾¹
    0.09
    ocale
    0.09
    æĺ¯åIJ¦åľ¨
    0.09
    æīijéĿ¢
    0.09
    åİŁæĸĩåĩºå¤Ħ
    0.09
    æĺ¯åIJ¦ä¸º
    0.09
     gär
    0.08
    ãģ¨æĢĿãģ£ãģŁãĤī
    0.08
    Activations Density 0.019%

    No Known Activations