© 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. 26543
    Prev
    Next
    INDEX
    Explanations

    principles and assumptions

    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
    undra
    -0.09
     xả
    -0.08
    lix
    -0.08
    llen
    -0.07
    eus
    -0.07
    idik
    -0.07
    ocat
    -0.07
    çģ°å¿ĥ
    -0.07
     ÐľÐ¾Ñģ
    -0.07
    NetMessage
    -0.07
    POSITIVE LOGITS
     Principle
    0.09
     principle
    0.09
     consistency
    0.07
    åİŁåĪĻ
    0.07
     пÑĢинÑĨип
    0.07
    inciple
    0.07
     пÑĢинÑĨи
    0.07
     principles
    0.07
    ä¸Ģèĩ´æĢ§
    0.07
     пÑĢинÑĨипе
    0.07
    Activations Density 0.011%

    No Known Activations