© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17290
    Prev
    Next
    INDEX
    Explanations

    temperature in Fahrenheit (°F)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİ©
    -0.06
    oufl
    -0.06
    opportun
    -0.06
    bid
    -0.06
    аÑĤÑĭ
    -0.06
    ä¹ĭäºĮ
    -0.06
    owing
    -0.06
     :</
    -0.06
    bury
    -0.05
    ats
    -0.05
    POSITIVE LOGITS
    venes
    0.05
     Incre
    0.05
    å¤ļåĬł
    0.05
    ensee
    0.05
    kle
    0.05
    ÑĨеп
    0.05
    åħļç»Ħ书记
    0.05
    cko
    0.05
    åįģå¹´åīį
    0.05
     kie
    0.05
    Activations Density 0.001%

    No Known Activations