© 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. 20572
    Prev
    Next
    INDEX
    Explanations

    ancient civilized places and ideas

    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
     Migr
    -0.06
    Migration
    -0.06
    umpa
    -0.06
    asmus
    -0.06
    tiden
    -0.06
    aed
    -0.06
    roz
    -0.06
    好æ¶Īæģ¯
    -0.06
    ÙĨÙĪÙĨ
    -0.06
    gege
    -0.06
    POSITIVE LOGITS
     mar
    0.06
     oh
    0.06
    å½¹
    0.05
    åľĨ满èIJ½å¹ķ
    0.05
    he
    0.05
     bes
    0.05
     obr
    0.05
    æĪIJå°±
    0.05
    ả
    0.05
    lor
    0.05
    Activations Density 0.016%

    No Known Activations