© 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. 17244
    Prev
    Next
    INDEX
    Explanations

    Season , Edit , data

    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
    è°ĵä¹ĭ
    -0.06
    -0.06
    åĨįå°Ĩ
    -0.06
    çais
    -0.06
    iker
    -0.05
     Shuffle
    -0.05
    opp
    -0.05
    åıĺæĽ´ä¿¡æģ¯
    -0.05
    ocken
    -0.05
    eram
    -0.05
    POSITIVE LOGITS
    ноÑĢа
    0.05
     presto
    0.05
    ')}
    0.05
    apro
    0.05
     اÙĦÙĦÙĩÙIJ
    0.05
     Ata
    0.05
     Entsteh
    0.05
    ç°
    0.05
     overt
    0.05
    rott
    0.04
    Activations Density 0.003%

    No Known Activations