© 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. 15072
    Prev
    Next
    INDEX
    Explanations

    magnetic domain wall motion, topological defect

    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
    endere
    -0.07
    ÑĦаÑĢ
    -0.06
    chest
    -0.06
    åľºåIJĪ
    -0.06
    .Span
    -0.06
    èĦīæIJı
    -0.06
    èĢĥå¯Ł
    -0.06
    çĤľ
    -0.06
    ä¸įåĬł
    -0.06
    aning
    -0.06
    POSITIVE LOGITS
     defects
    0.08
    æķ°çĽ®
    0.07
    èĥŀ
    0.07
    emberg
    0.07
     tears
    0.07
    IBM
    0.07
     rop
    0.07
     nicknamed
    0.07
    åĪĥ
    0.07
     undone
    0.07
    Activations Density 0.007%

    No Known Activations