© 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. 2749
    Prev
    Next
    INDEX
    Explanations

    vitamin D/E

    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
    åĬłæĭ¿å¤§
    -0.09
    illons
    -0.07
    umpf
    -0.07
    емÑĥ
    -0.07
    å¹´åĮĹ京
    -0.07
    à¹Ĥà¸ķ
    -0.07
    аÑĤÑĭ
    -0.07
    æ²³æºIJ
    -0.07
    untut
    -0.07
    ìķĦíĬ¸
    -0.07
    POSITIVE LOGITS
    çıĬ
    0.07
    麻
    0.06
    stra
    0.06
    ä¿
    0.06
    ä¿Ŀ
    0.06
    usch
    0.06
    land
    0.06
    IDA
    0.06
    çĭ®
    0.06
    ç´ł
    0.06
    Activations Density 0.465%

    No Known Activations