© 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. 7908
    Prev
    Next
    INDEX
    Explanations

    catalyst sites acidity

    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
    shed
    -0.08
    åĽĽèĤ¢
    -0.08
    èĩªæĦ¿
    -0.07
    æ´Ĺ澡
    -0.07
    涮
    -0.07
    shal
    -0.07
    游泳
    -0.07
    ç¼ĸåĪ¶
    -0.07
    çĤ¹åIJį
    -0.07
     Divers
    -0.06
    POSITIVE LOGITS
     acidity
    0.08
    oser
    0.08
    à°Łà°¿
    0.07
     catal
    0.07
    éħ°
    0.07
    çĻ»è®°è¯ģ
    0.07
    éħ¸æĢ§
    0.07
    denes
    0.07
     sites
    0.07
    ç¥ŀé¾Ļ
    0.07
    Activations Density 0.011%

    No Known Activations