© 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. 23546
    Prev
    Next
    INDEX
    Explanations

    pension, houses, Found, jsonp

    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
    oted
    -0.09
    atron
    -0.09
    å®ģæĦ¿
    -0.09
    MSG
    -0.09
    åĮ¡
    -0.09
    otton
    -0.08
     mosque
    -0.08
    æľ¦èĥ§
    -0.08
    年产
    -0.08
    æŁĦ
    -0.08
    POSITIVE LOGITS
    大åħ¨
    0.09
    æļ
    0.08
    nen
    0.08
    سÙĪر
    0.08
    ÑĢеÑģ
    0.08
    lık
    0.08
    UDP
    0.08
    综åIJĪä½ĵ
    0.08
    WithDuration
    0.08
    ientes
    0.08
    Activations Density 0.002%

    No Known Activations