© 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. 17605
    Prev
    Next
    INDEX
    Explanations

    corner and intersection

    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
    noch
    -0.06
    sama
    -0.06
    ellig
    -0.06
    ême
    -0.05
    olesale
    -0.05
    æ°´å¹³
    -0.05
    çªĦ
    -0.05
    beda
    -0.05
    ttes
    -0.05
    ÃŃstica
    -0.05
    POSITIVE LOGITS
     multid
    0.07
     corner
    0.06
    åĮħåĽ´
    0.06
    ut
    0.06
    Corner
    0.06
     intersections
    0.06
    åĽĽæĸ¹
    0.06
    Īĺ
    0.06
     intersection
    0.05
     Corner
    0.05
    Activations Density 0.082%

    No Known Activations