© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16865
    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
    åĬ¡
    -0.06
     COMPR
    -0.06
    isola
    -0.06
    vem
    -0.06
    brid
    -0.06
     Compre
    -0.06
     побли
    -0.06
    ãģĨãģ¡ãģ«
    -0.06
    ivr
    -0.06
    fully
    -0.06
    POSITIVE LOGITS
    bers
    0.07
    aux
    0.06
    Ø©
    0.06
    osis
    0.05
    åıªä¸įè¿ĩæĺ¯
    0.05
    бÑĥдÑĮÑĤе
    0.05
    ation
    0.05
    第ä¸īèĢħ
    0.05
    ering
    0.05
    ing
    0.05
    Activations Density 0.000%

    No Known Activations