© 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. 15460
    Prev
    Next
    INDEX
    Explanations

    introduction, decent, steam, circumstances, additional, serious

    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
    etid
    -0.08
    èİĵ
    -0.07
    arti
    -0.07
     ниÑħ
    -0.06
    .conf
    -0.06
    ekt
    -0.06
    erti
    -0.06
    Æ°Æ¡ng
    -0.06
    è¿ĻäºĽäºĭ
    -0.06
    ä¹ĺçĿĢ
    -0.06
    POSITIVE LOGITS
    Ñħий
    0.07
    ãģ¨ãģĦãģĨãģ®ãģ¯
    0.07
    atrix
    0.07
     indeed
    0.07
     ||=
    0.07
    oogle
    0.07
    为ä»Ģä¹Īä¼ļ
    0.07
     Roque
    0.07
    PLY
    0.07
     Allan
    0.06
    Activations Density 0.292%

    No Known Activations