© 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. 30997
    Prev
    Next
    INDEX
    Explanations

    shaping and forming processes

    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
    å½ķ
    -0.06
    entos
    -0.06
    æ»´æ»´
    -0.06
    éĹ¹
    -0.06
    æĪ¿ä¸ľ
    -0.06
    æ²½
    -0.06
    å¯ĦåŃĺ
    -0.06
    æ¸ħçĤ¹
    -0.06
    ä»İçİ°åľ¨å¼Ģå§ĭ
    -0.06
    eno
    -0.06
    POSITIVE LOGITS
    æĪIJåŀĭ
    0.11
    æĪIJå½¢
    0.10
     Into
    0.09
    Into
    0.08
     deformation
    0.08
     sizing
    0.08
    å®ļåŀĭ
    0.08
     deform
    0.08
    into
    0.08
    åİĭä¸ĭ
    0.08
    Activations Density 0.051%

    No Known Activations