© 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. 31342
    Prev
    Next
    INDEX
    Explanations

    movement and trend

    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
    åįĥåı¤
    -0.07
     etern
    -0.07
    天çĶŁ
    -0.07
    丧失
    -0.07
     ordinarily
    -0.06
     useless
    -0.06
     famously
    -0.06
    aja
    -0.06
    åIJ«
    -0.06
    çIJĨ论ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    åı¯åĸľ
    0.13
     recent
    0.11
    主è¦ģéĽĨä¸Ńåľ¨
    0.11
    ä¹ŁéĢIJæ¸IJ
    0.11
    带åĬ¨äºĨ
    0.11
    ä¸įä¹ı
    0.11
    äºĨä¸Ģæī¹
    0.11
     notable
    0.10
    以赴
    0.10
     progress
    0.10
    Activations Density 0.412%

    No Known Activations