© 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. 61921
    Prev
    Next
    INDEX
    Explanations

    flag related terms

    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
    ationally
    -0.09
    ä¸įèĥľæĶ¶
    -0.08
    odos
    -0.08
    åĪ°çļĦ
    -0.07
    erer
    -0.07
    ság
    -0.07
    ắt
    -0.07
    éĿ¢å¹¿
    -0.07
    illon
    -0.07
    ained
    -0.07
    POSITIVE LOGITS
    áŁĭ
    0.09
    less
    0.09
    avourites
    0.08
    pole
    0.08
    UTURE
    0.08
    furter
    0.08
    crest
    0.07
    avourite
    0.07
    stellung
    0.07
    bearer
    0.07
    Activations Density 0.051%

    No Known Activations