© 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. 18119
    Prev
    Next
    INDEX
    Explanations

    failure of

    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
    повÑĸда
    -0.08
    ä¸įå·®
    -0.08
    resta
    -0.08
    endas
    -0.08
     afforded
    -0.08
    åıĹçĸ«æĥħå½±åĵį
    -0.07
    ä¸įäºī
    -0.07
    azza
    -0.07
    abda
    -0.07
    umer
    -0.07
    POSITIVE LOGITS
    è¿ĽèĢĮ
    0.10
     voire
    0.10
    继èĢĮ
    0.10
    æĹłæ³ķæŃ£å¸¸
    0.10
    æĦıæĥ³ä¸įåĪ°çļĦ
    0.10
    ä»İèĢĮ导èĩ´
    0.09
    çĶļèĩ³
    0.09
    à¸ķามมา
    0.09
    严éĩįæŶ
    0.09
    ä¹ĥèĩ³
    0.08
    Activations Density 0.182%

    No Known Activations