© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19117
    Prev
    Next
    INDEX
    Explanations

    polynomial terms

    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
     toss
    -0.06
    vaard
    -0.06
     наÑģÑĤÑĢой
    -0.06
     Sej
    -0.06
    æľĢæĸ°åıijå¸ĥ
    -0.06
    egu
    -0.05
    éļıæīĭ
    -0.05
     capo
    -0.05
    stüt
    -0.05
     nost
    -0.05
    POSITIVE LOGITS
    ides
    0.06
    سا
    0.05
    ä¸įè§ģäºĨ
    0.05
    kannya
    0.05
    æ¢ĵ
    0.05
    åĨĻåľ¨
    0.05
    دÛĮد
    0.05
    ubl
    0.05
    steen
    0.05
    edly
    0.05
    Activations Density 0.001%

    No Known Activations