© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19310
    Prev
    Next
    INDEX
    Explanations

    temporary or temporarily

    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
     thầm
    -0.08
    estions
    -0.08
    omba
    -0.08
    entren
    -0.08
    hints
    -0.08
    ä½ĵåĪ¶æĶ¹éĿ©
    -0.07
    weiten
    -0.07
    æĹłè¨Ģ
    -0.07
    累累
    -0.07
    QUEST
    -0.07
    POSITIVE LOGITS
    /temp
    0.15
    orary
    0.11
    ëĤĺë§Ī
    0.11
    åį³éĢĿ
    0.10
    aneous
    0.10
    æĢ§çļĦ
    0.10
     temporary
    0.10
    aneously
    0.09
    orarily
    0.09
    临æŶ
    0.09
    Activations Density 0.066%

    No Known Activations