© 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. 18703
    Prev
    Next
    INDEX
    Explanations

    week

    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
    æľīæķĪçļĦ
    -0.06
    anon
    -0.06
    عاÙħ
    -0.05
    truc
    -0.05
     effectively
    -0.05
     subdiv
    -0.05
     efect
    -0.05
    è¿Ľä¸ĢæŃ¥åĬłå¼º
    -0.05
     effective
    -0.05
    ź
    -0.05
    POSITIVE LOGITS
    ä¸Ĭä»»
    0.06
    ARA
    0.06
    igner
    0.06
    iaux
    0.06
    æĸĩåĮĸå¹¿åľº
    0.05
     hn
    0.05
    неÑĤо
    0.05
    é½IJ家
    0.05
    ufs
    0.05
    idge
    0.05
    Activations Density 0.009%

    No Known Activations