© 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. 18350
    Prev
    Next
    INDEX
    Explanations

    known prior art

    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
    ä¸ĭåIJĮ
    -0.06
    عÙĬÙĨ
    -0.06
    iska
    -0.06
    åĩĨå¤ĩ好äºĨåIJĹ
    -0.06
     readiness
    -0.06
    udence
    -0.06
    åľ¨åľº
    -0.06
    åħ¬è¯īæľºåħ³
    -0.06
     Entrada
    -0.06
    tein
    -0.05
    POSITIVE LOGITS
    kip
    0.05
    åĪ°ä¸Ģ个
    0.05
    reiro
    0.05
     иÑĤо
    0.05
    sé
    0.05
    ä»ĸ们å°Ĩ
    0.05
    åħ¶åIJį
    0.05
     Dec
    0.05
    lare
    0.05
     a
    0.05
    Activations Density 0.001%

    No Known Activations