© 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. 4099
    Prev
    Next
    INDEX
    Explanations

    standard or norm

    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
    çħ§æł·
    -0.09
    ORK
    -0.08
    ä¸ĢåĪ»
    -0.08
    caled
    -0.08
    appers
    -0.08
     precis
    -0.07
    æĥĬéĻ©
    -0.07
    æĤį
    -0.07
    çIJĨ论水平
    -0.07
    Scaled
    -0.07
    POSITIVE LOGITS
    é»ĺ认
    0.10
     presumed
    0.09
     implicitly
    0.08
     restrict
    0.08
    ä¸įè¨Ģ
    0.08
     reasonable
    0.08
     assumed
    0.08
    ä¹łæĥ¯æĢ§
    0.07
    è¡ĢèĦī
    0.07
     restricting
    0.07
    Activations Density 0.007%

    No Known Activations