© 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. 17760
    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
     Ann
    -0.05
    chsel
    -0.05
    лÑıÑĢ
    -0.05
    âĤ¬.
    -0.05
    çīºçī²
    -0.05
    kowski
    -0.04
    ake
    -0.04
    ney
    -0.04
    ulla
    -0.04
    åıįæĺł
    -0.04
    POSITIVE LOGITS
    æ¡¥éķĩ
    0.08
    صرÙĬØ©
    0.08
     difficulty
    0.08
     bess
    0.07
    sau
    0.07
    tir
    0.07
    berger
    0.07
    fav
    0.06
     Breitbart
    0.06
    è¶ħè¿ĩ约
    0.06
    Activations Density 0.000%

    No Known Activations