© 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. 22024
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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¸Ħà¸ĩ
    -0.05
    corp
    -0.05
    orp
    -0.05
    æĪijåħĪ
    -0.05
    ä¸įåıĬ
    -0.05
    ibel
    -0.05
    kah
    -0.05
     pun
    -0.05
    åŃĺ
    -0.05
    åħĪåĪ°
    -0.05
    POSITIVE LOGITS
    åĽłä¸ºè¿Ļ
    0.06
    ambe
    0.06
    æ¸ħ宫
    0.06
    以åıĬä¸İ
    0.05
     passaggi
    0.05
    æĥ¯
    0.05
     Profession
    0.05
    ussi
    0.05
    ongen
    0.05
     bayan
    0.05
    Activations Density 0.000%

    No Known Activations