© 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. 27813
    Prev
    Next
    INDEX
    Explanations

    picking sequences

    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
    onos
    -0.08
    æĹ¶è®¸
    -0.08
    åĵªéĩĮ
    -0.08
    æĹ¥ä»İ
    -0.07
    çħ
    -0.07
    Ñijд
    -0.07
    ä¸įä¹±
    -0.07
    æī
    -0.07
    ä¿ŀ
    -0.07
    ibble
    -0.07
    POSITIVE LOGITS
    éĥ½æľīåĵªäºĽ
    0.07
    æŁIJä¸Ģ个
    0.07
    æīĢæľīçļĦ
    0.07
    çĶµæ°Ķ
    0.07
    طة
    0.07
    defer
    0.06
    że
    0.06
    åĪ¶è®¢
    0.06
    amax
    0.06
    ä¸įäºĪåıĹçIJĨ
    0.06
    Activations Density 0.075%

    No Known Activations