© 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. 17685
    Prev
    Next
    INDEX
    Explanations

    existentialism and existence

    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
    软åĮĸ
    -0.05
     sug
    -0.05
     varying
    -0.05
    ym
    -0.05
    inc
    -0.05
     calm
    -0.05
    orig
    -0.04
    ra
    -0.04
    imas
    -0.04
     buffered
    -0.04
    POSITIVE LOGITS
    ç«ĭå¾·
    0.07
    ÛĮدا
    0.06
    èĮ«
    0.06
    åįĹçľģ
    0.06
     vert
    0.06
    ধান
    0.06
     freedom
    0.06
    åŃĺåľ¨æĦŁ
    0.06
    à¹Ģà¸Ľà¸¥à¹Īา
    0.06
    electron
    0.06
    Activations Density 0.001%

    No Known Activations