© 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. 18052
    Prev
    Next
    INDEX
    Explanations

    tighty-whiteys, Lui Lui beckons, pom pom, Ba Da Bing Records

    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
    iá»ģu
    -0.06
    漪
    -0.05
    uzzi
    -0.05
    usz
    -0.05
    ager
    -0.05
    å¹ķ
    -0.05
    ulus
    -0.05
    æ®ī
    -0.05
     merito
    -0.05
    ãģŀ
    -0.05
    POSITIVE LOGITS
    ([^
    0.06
    ä¸Ģ家
    0.06
    ERM
    0.06
    wier
    0.06
    åĤ¬çľł
    0.06
    èº
    0.06
    æĸ°å¤©åľ°
    0.06
     bada
    0.06
    oting
    0.06
    observ
    0.05
    Activations Density 0.038%

    No Known Activations