© 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. 17497
    Prev
    Next
    INDEX
    Explanations

    race, religion, culture, color, identity

    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
    anto
    -0.06
    ography
    -0.05
    ung
    -0.05
     l
    -0.05
    pace
    -0.05
     optimization
    -0.05
    quent
    -0.05
    ology
    -0.05
    nt
    -0.05
     channel
    -0.05
    POSITIVE LOGITS
     Acomp
    0.07
    rell
    0.06
    heim
    0.06
    槻
    0.06
    ensibly
    0.06
    è¨Ģæĥħå°ı说
    0.06
    ISCO
    0.06
    åĩºæĿ¥ãģ¾ãģĹãģŁ
    0.06
    umbo
    0.06
    .Constant
    0.06
    Activations Density 0.001%

    No Known Activations