© 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. 12674
    Prev
    Next
    INDEX
    Explanations

    logic and functionality

    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
    ÑģÑĤеÑĢ
    -0.08
    erot
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    å¸Ĥåľºä¸ĬçļĦ
    -0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    amera
    -0.07
    sters
    -0.06
     extrad
    -0.06
    winkel
    -0.06
     íĹĪ
    -0.06
    POSITIVE LOGITS
    ORK
    0.09
    æĸ¯é¡¿
    0.06
     logic
    0.06
    Sta
    0.06
    ork
    0.06
     Rund
    0.06
    arkan
    0.06
    chs
    0.06
    bef
    0.06
    oston
    0.06
    Activations Density 0.020%

    No Known Activations