© 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. 11467
    Prev
    Next
    INDEX
    Explanations

    retain the above copyright notice

    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
    å£ķ
    -0.08
    allon
    -0.08
    SubMenu
    -0.07
    åħļå§Ķå§Ķåijĺ
    -0.07
    UNIX
    -0.07
    éĻį
    -0.07
    peater
    -0.07
    äºĮå¹´
    -0.07
    åĢ¼å¾ĹæľŁå¾ħ
    -0.07
     Domingo
    -0.07
    POSITIVE LOGITS
    ä¸įå¾Ĺ
    0.09
     attribution
    0.09
     honorable
    0.08
    åİŁä½ľèĢħ
    0.08
     Chauff
    0.07
    ä¿ĿæĮģ
    0.07
     Redistributions
    0.07
    ä¸įå°ijäºİ
    0.07
     acknowledgement
    0.06
    /reference
    0.06
    Activations Density 0.331%

    No Known Activations