© 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. 47374
    Prev
    Next
    INDEX
    Explanations

    movement direction and change

    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
    ggi
    -0.08
    iami
    -0.08
    æİ
    -0.08
    γκα
    -0.08
    çļĦåħ¨éĥ¨
    -0.08
    å½±åĵįäºĨ
    -0.08
    aglio
    -0.08
    ä¾Ľå¤§å®¶
    -0.08
     McGr
    -0.08
    åIJĦ项è§Ħç«łåĪ¶åº¦
    -0.07
    POSITIVE LOGITS
    æ¯ı次
    0.10
    æ¯ı次éĥ½
    0.10
    æ¯ıä¸Ģ次
    0.08
    大æŃ¥
    0.08
    ä¸Ĭä¸Ģ次
    0.08
     progress
    0.08
    ä¸ĢæŃ¥
    0.07
     Step
    0.07
    æ¯ıä¸ĢæŃ¥
    0.07
    åģļä¸Ģ次
    0.07
    Activations Density 0.008%

    No Known Activations