© 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. 30264
    Prev
    Next
    INDEX
    Explanations

    Western cultures and countries

    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
    å²Ľä¸Ĭ
    -0.10
    å²Ľ
    -0.09
    째
    -0.09
     süre
    -0.09
    lien
    -0.09
    èŤ
    -0.09
    çĤĴ
    -0.09
    uppen
    -0.09
    çĦ¶æĺ¯
    -0.09
    æ¸ħé¦Ļ
    -0.09
    POSITIVE LOGITS
    ä¿¡ä»»
    0.10
    æĸĩæĺİ
    0.09
     дÑĥÑħ
    0.09
    arrant
    0.09
    ization
    0.08
    åĮĸè¿Ľç¨ĭ
    0.08
    西æĸ¹
    0.08
    以èĩ´
    0.08
     civilization
    0.08
    è°ļ
    0.08
    Activations Density 0.043%

    No Known Activations