© 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. 38028
    Prev
    Next
    INDEX
    Explanations

    temporal ordering and timing

    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
    åĩłå®¶
    -0.08
     borderWidth
    -0.07
    ainty
    -0.07
    åIJĪä½ľåħ±èµ¢
    -0.07
    à²Łà³įà²Ł
    -0.07
    .createObject
    -0.07
    äºĴæį¢
    -0.07
    åij¼
    -0.07
    åĢĭæĢ§
    -0.07
    ,assign
    -0.07
    POSITIVE LOGITS
     tempor
    0.13
    æŶéĹ´çĤ¹
    0.12
     temporal
    0.11
     timing
    0.11
    çļĦæŶéĹ´
    0.11
     ÏĩÏģον
    0.11
    æŶéĹ´èĬĤçĤ¹
    0.10
     timeframe
    0.10
     Timing
    0.10
    æŶéĹ´æ®µ
    0.10
    Activations Density 0.391%

    No Known Activations