© 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. 61021
    Prev
    Next
    INDEX
    Explanations

    no need

    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
    åĩĨ
    -0.08
    orate
    -0.07
    çļĦä¸ĢçĤ¹
    -0.07
    åį´æ²¡
    -0.07
     eman
    -0.07
    iven
    -0.07
    è¿Ļæł·ä¸Ģ个
    -0.07
    çļĦä¸Ģ个
    -0.06
    %E
    -0.06
    注è§Ĩ
    -0.06
    POSITIVE LOGITS
     unnecessary
    0.08
     Zal
    0.08
    hiba
    0.07
    ä¸įå¿ħè¦ģ
    0.07
    ä¸įéľĢè¦ģ
    0.07
    äºĮè¯Ŀ
    0.07
    åŃĹåı·
    0.07
    ä¹Łä¸įçĶ¨
    0.07
    å¤ļä½ĻçļĦ
    0.07
     ëĵ¤ìĸ´
    0.07
    Activations Density 0.016%

    No Known Activations