© 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. 21689
    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
    山大
    -0.06
    thal
    -0.05
    -present
    -0.05
    çĻŀ
    -0.05
    åĵī
    -0.05
     Mig
    -0.05
    fatal
    -0.05
    åIJ¸
    -0.05
     Perp
    -0.05
    对该
    -0.05
    POSITIVE LOGITS
    unu
    0.06
    egers
    0.06
    rior
    0.06
    xis
    0.06
    egen
    0.05
    olong
    0.05
    亢
    0.05
    /OR
    0.05
    inni
    0.05
     лекаÑĢ
    0.05
    Activations Density 0.000%

    No Known Activations