© 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. 20631
    Prev
    Next
    INDEX
    Explanations

    broad coverage or range

    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
    зло
    -0.08
    alda
    -0.08
    usal
    -0.07
     MIS
    -0.07
    MISS
    -0.07
    ä¹Ŀä¹Ŀ
    -0.07
    ORK
    -0.07
    æĽ´çĶŁ
    -0.07
    ually
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    POSITIVE LOGITS
    ened
    0.12
    ening
    0.11
    esso
    0.09
    erus
    0.08
    ings
    0.07
    ed
    0.07
    åīĤ
    0.07
    smith
    0.07
    ÛĮ
    0.07
     dovuto
    0.07
    Activations Density 0.008%

    No Known Activations