© 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. 18552
    Prev
    Next
    INDEX
    Explanations

    simple or simplified versions/guides/reports

    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
     Fisher
    -0.05
    å°±æĺ¯æĪij们çļĦ
    -0.05
     pis
    -0.05
    igu
    -0.05
    è¦ģ约
    -0.05
     >
    -0.05
    aut
    -0.05
    ÑĤай
    -0.05
    Flip
    -0.05
     set
    -0.05
    POSITIVE LOGITS
    å¾Īå¤ļ次
    0.07
    å¾ĪæĹ©å°±
    0.07
     ÃŃch
    0.07
     Aleman
    0.06
    éļĶ天
    0.06
    rus
    0.06
    马åĬĽ
    0.06
     banyak
    0.06
    antly
    0.06
    ÙĪغ
    0.06
    Activations Density 0.005%

    No Known Activations