© 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. 34407
    Prev
    Next
    INDEX
    Explanations

    point A to point B

    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
    åĿIJåľ¨ä¸Ģèµ·
    -0.07
     trickle
    -0.07
    åı°ä¸ĭ
    -0.07
    ãĤ¶ãĥ¼
    -0.07
    ä¸įæĶ¾
    -0.06
    æĶ¾åľ¨ä¸Ģèµ·
    -0.06
     Ñĥмол
    -0.06
    ä¸Ĭå²Ĺ
    -0.06
    åľ¨ä¸ĢæĹģ
    -0.06
     chôm
    -0.06
    POSITIVE LOGITS
    缮çļĦåľ°
    0.11
    éģ¿å¼Ģ
    0.10
    éĢīæĭ©ä¸Ģ个
    0.09
    çļĦæĸ¹åIJij
    0.09
    æĸ¹åIJijçļĦ
    0.09
    Direction
    0.08
     direction
    0.08
     directional
    0.08
     perpendicular
    0.08
    æĸ¹åIJij
    0.08
    Activations Density 0.048%

    No Known Activations