© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21642
    Prev
    Next
    INDEX
    Explanations

    particularly, most, early

    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
    ildir
    -0.08
     broader
    -0.08
    ä¹Łä¸įç®Ĺ
    -0.07
     Except
    -0.07
     albeit
    -0.07
     unto
    -0.07
    outline
    -0.07
    éĿ¢éĿ¢
    -0.07
    िस
    -0.07
    åIJĪæł¼çļĦ
    -0.07
    POSITIVE LOGITS
     particularly
    0.17
    çī¹ãģ«
    0.16
    尤为
    0.16
    particularly
    0.16
     íĬ¹íŀĪ
    0.16
    å°¤åħ¶
    0.15
     Particularly
    0.15
     especially
    0.15
     оÑģобенно
    0.15
    å°¤åħ¶æĺ¯
    0.15
    Activations Density 0.475%

    No Known Activations