© 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. 50171
    Prev
    Next
    INDEX
    Explanations

    frequently oscillating periods

    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
     اÙĦÙħج
    -0.08
    uz
    -0.07
    åħį
    -0.07
    uÃŃ
    -0.07
     Bare
    -0.06
    umper
    -0.06
    åħ«è§Ĵ
    -0.06
    empt
    -0.06
    plen
    -0.06
    å¿ĥéħ¸
    -0.06
    POSITIVE LOGITS
    åıªæľīä¸Ģ次
    0.13
    åıªæľīä¸Ģ个
    0.10
    两次
    0.09
    éĶĻè¿ĩ
    0.09
    æľī两个
    0.08
    å°±æľīåı¯èĥ½
    0.08
    ä¸ĢåĽŀ
    0.08
    å°±åı¯èĥ½
    0.08
    æīįæľīåı¯èĥ½
    0.08
    è¿ĺæľīæľºä¼ļ
    0.08
    Activations Density 0.002%

    No Known Activations