© 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. 13117
    Prev
    Next
    INDEX
    Explanations

    prime factors of

    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
     shaved
    -0.07
     berb
    -0.07
    å¿ĥå®ī
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
    perator
    -0.07
    æĺ¯ç¬¬ä¸Ģ
    -0.07
     '_',
    -0.07
    anga
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    cales
    -0.07
    POSITIVE LOGITS
    ละà¹Ģà¸Ńียà¸Ķ
    0.07
    æĺ¯ä¸Ģ座
    0.07
    å½»åºķ
    0.07
    ifact
    0.07
    ÃĤY
    0.07
     écl
    0.07
    大åħ¬
    0.07
    éĩĮæĸ¯
    0.06
    å½»åºķçļĦ
    0.06
    åĪĨ解
    0.06
    Activations Density 0.008%

    No Known Activations