© 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. 21119
    Prev
    Next
    INDEX
    Explanations

    #include <header>

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ogn
    -0.06
     //_
    -0.05
    åľĨ
    -0.05
    awy
    -0.05
    odate
    -0.05
     عÙĨÙĩ
    -0.05
    ç²
    -0.05
    mine
    -0.05
     round
    -0.05
     f
    -0.05
    POSITIVE LOGITS
    eman
    0.06
    ило
    0.06
    herr
    0.06
    onium
    0.05
     Downs
    0.05
    помним
    0.05
    วาย
    0.05
    bern
    0.05
    zens
    0.05
    ç´¯çļĦ
    0.05
    Activations Density 0.023%

    No Known Activations