© 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. 16951
    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
    ulet
    -0.06
    lew
    -0.06
    alii
    -0.05
    aggio
    -0.05
    éĻµ
    -0.05
    ELLI
    -0.05
    anine
    -0.05
    ellit
    -0.05
    大çİĭ
    -0.05
    inach
    -0.05
    POSITIVE LOGITS
     تخصص
    0.05
    ç¶
    0.05
    åıįåIJij
    0.05
    зо
    0.05
    perl
    0.05
    adapt
    0.05
    edis
    0.05
     adatt
    0.05
    ever
    0.05
     Stabil
    0.05
    Activations Density 0.000%

    No Known Activations