© 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. 21590
    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
     reap
    -0.07
    vig
    -0.07
    Ñħина
    -0.06
    гÑĢан
    -0.06
     إذÙĨ
    -0.06
    áles
    -0.06
    ק×Ķ
    -0.06
    InputChange
    -0.06
    ytu
    -0.06
    imple
    -0.06
    POSITIVE LOGITS
    upon
    0.05
     “
    0.05
     Recon
    0.05
    ï¸İ
    0.05
    енок
    0.05
    ضÙħاÙħ
    0.05
     Ex
    0.05
     dec
    0.05
    оÑĢи
    0.04
     Dec
    0.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.