© 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. 17205
    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
    -0.06
    кÑĥп
    -0.05
    esc
    -0.05
    Ø®ÙĪا
    -0.05
    erecht
    -0.05
    å·¥ç¨ĭçŃī
    -0.05
    sted
    -0.05
    çada
    -0.05
    AVA
    -0.05
    Ń
    -0.05
    POSITIVE LOGITS
    å®ļ
    0.07
    HING
    0.06
    Sibling
    0.06
    urry
    0.06
    anter
    0.06
    eterangan
    0.06
    -now
    0.06
     deten
    0.05
    umble
    0.05
     cum
    0.05
    Activations Density 0.000%

    No Known Activations