© 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. 4424
    Prev
    Next
    INDEX
    Explanations

    conditions or exceptions

    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
     somewhat
    -0.07
     almost
    -0.07
    otropic
    -0.06
     heen
    -0.06
    à¸ŀึà¹Īà¸ĩ
    -0.06
    anes
    -0.06
    almost
    -0.06
    åľ°çIJĥä¸Ĭ
    -0.06
     lite
    -0.06
    ropic
    -0.06
    POSITIVE LOGITS
     necessary
    0.09
    å¿ħè¦ģ
    0.09
    æľīå¿ħè¦ģ
    0.09
    à¸Īำà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    EEDED
    0.08
    å¿ħè¦ģçļĦ
    0.08
     needed
    0.08
    needed
    0.08
    ecessary
    0.08
     erw
    0.08
    Activations Density 0.041%

    No Known Activations