© 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. 16985
    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
    .tom
    -0.05
     bill
    -0.05
    大åIJĮ
    -0.05
     Jun
    -0.05
    èĭ¦
    -0.05
    id
    -0.05
    ...
    -0.05
     don
    -0.05
     riff
    -0.04
    POSITIVE LOGITS
    ascal
    0.07
     legalize
    0.07
    ellerie
    0.07
    amble
    0.07
    écu
    0.07
    kere
    0.07
     Cual
    0.07
     sério
    0.07
    trl
    0.06
    енÑĤа
    0.06
    Activations Density 0.000%

    No Known Activations