© 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. 18677
    Prev
    Next
    INDEX
    Explanations

    to sort

    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
    ibe
    -0.08
    缸åºĶ
    -0.07
    —that
    -0.07
    ibar
    -0.07
     subsequently
    -0.07
    å¿ĥæĤ¦
    -0.07
    çĽ¸å¯¹åºĶçļĦ
    -0.07
    Ø·ÙĦ
    -0.07
    kin
    -0.07
    æŃ¤é¡¹
    -0.07
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.10
    ïs
    0.08
     ìĿ¼ëĭ¨
    0.08
    ีส
    0.07
     먼ìłĢ
    0.07
     firstly
    0.07
     Ø£ÙĪÙĦا
    0.07
    æĹ¢è¦ģ
    0.07
    åħĪæĬĬ
    0.07
    åĩ¡æľ¬ç½ij注æĺİ
    0.07
    Activations Density 0.042%

    No Known Activations