© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34127
    Prev
    Next
    INDEX
    Explanations

    Middle East

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æ¨Ł
    -0.10
    å°ı女åŃ©
    -0.10
    è°¶
    -0.10
    é³Ĺ
    -0.10
    strup
    -0.10
    éĢĥèĦ±
    -0.10
    æľªç»ı
    -0.10
    æĦŁåĨĴ
    -0.10
    DED
    -0.09
     اÙĦتش
    -0.09
    POSITIVE LOGITS
    迪æĭľ
    0.12
    éĺ¿æĭī伯
    0.10
     Arab
    0.10
     Cairo
    0.10
    ä¸Ń举
    0.09
     polls
    0.09
     LIS
    0.09
     Arabia
    0.08
    iza
    0.08
     Arabic
    0.08
    Activations Density 0.139%

    No Known Activations