© 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. 46823
    Prev
    Next
    INDEX
    Explanations

    was granted, proceeds to, raised more, has revealed

    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
    ÏģίÏĤ
    -0.08
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.08
    顾åIJįæĢĿä¹ī
    -0.08
    ritel
    -0.08
    ủng
    -0.08
    estig
    -0.07
    ÑĢид
    -0.07
    ä»İ天
    -0.07
    lacht
    -0.07
     '_',
    -0.07
    POSITIVE LOGITS
    idis
    0.06
    :disable
    0.06
     latter
    0.06
    ä¼ĹæīĢåij¨çŁ¥
    0.06
    åīįèĢħ
    0.06
    ens
    0.06
    fa
    0.06
    :
    0.06
    stad
    0.06
    en
    0.05
    Activations Density 0.655%

    No Known Activations