© 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. 21486
    Prev
    Next
    INDEX
    Explanations

    circum openings

    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
    elius
    -0.05
     lam
    -0.05
    riot
    -0.05
     hal
    -0.05
    aked
    -0.05
     ‘
    -0.05
    æĺ
    -0.05
    traits
    -0.05
     :-)
    -0.05
    ä¼ĺçĤ¹
    -0.05
    POSITIVE LOGITS
    ara
    0.06
    rod
    0.06
    yel
    0.06
    rogram
    0.06
    ARA
    0.05
     ìļ©
    0.05
     دÙĪÙĦ
    0.05
    ÑĨио
    0.05
    пÑĥ
    0.05
    åıĬ以ä¸ĬåѦåİĨ
    0.05
    Activations Density 0.017%

    No Known Activations