© 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. 22031
    Prev
    Next
    INDEX
    Explanations

    events and outcomes

    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
    à¸Ĩ
    -0.06
    åıijçİ°
    -0.05
    ãģĨãģ¡ãģ«
    -0.05
    aml
    -0.05
    laÅŁ
    -0.05
    æł¼æĭī
    -0.05
    .ba
    -0.05
    æĢł
    -0.05
    å¿ĥäºĨ
    -0.05
    åĴ½åĸī
    -0.05
    POSITIVE LOGITS
    æĹłæķ°æ¬¡
    0.06
    ç®ĢåĮĸ
    0.06
    urbed
    0.06
    uate
    0.06
    ienne
    0.06
    tah
    0.05
    frau
    0.05
    brook
    0.05
     autant
    0.05
     mess
    0.05
    Activations Density 0.037%

    No Known Activations