© 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. 22080
    Prev
    Next
    INDEX
    Explanations

    selected/imposed/specified/generated/obtained/created/measured/detected

    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
    温æļĸçļĦ
    -0.06
    ravi
    -0.06
    çļĦéĤ£ä¸Ģ天
    -0.06
    æľ¨æĸ¯
    -0.05
    åIJĪéĢĤçļĦ
    -0.05
    çIJ
    -0.05
    dddd
    -0.05
     racks
    -0.05
    iy
    -0.05
    ocks
    -0.05
    POSITIVE LOGITS
     sparing
    0.06
    å¥Īä½ķ
    0.06
    osph
    0.06
    çģ«çĥ§
    0.06
    ellas
    0.06
     Seger
    0.06
    upati
    0.05
    urse
    0.05
    çľŁä¼ª
    0.05
    åIJĦ
    0.05
    Activations Density 0.025%

    No Known Activations