© 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. 26759
    Prev
    Next
    INDEX
    Explanations

    Iran and Iranian references

    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
    еÑģ
    -0.09
    æ¹¾åĮº
    -0.09
     mnemonic
    -0.09
    aÅĤ
    -0.09
    razil
    -0.09
    ä¼Ļ
    -0.09
    ä½¼
    -0.09
     Gambling
    -0.09
    粤港澳
    -0.09
    hear
    -0.09
    POSITIVE LOGITS
     Tehran
    0.09
    æĢ»ä¹ĭ
    0.08
    èĽī
    0.08
     itemprop
    0.08
    -backed
    0.08
    Boston
    0.08
    bows
    0.08
    åľ°æ¯¯
    0.08
    ä¼ĬæľĹ
    0.08
    yla
    0.08
    Activations Density 0.020%

    No Known Activations