© 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. 31942
    Prev
    Next
    INDEX
    Explanations

    "West Bank" and "Jerusalem" areas

    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
    é¼İ
    -0.09
    mailto
    -0.09
    社ä¼ļæķĪçĽĬ
    -0.09
     Knight
    -0.09
    西æ¹ĸ
    -0.09
    ystems
    -0.08
    ç®Ģ便
    -0.08
    æī³
    -0.08
    ä¸Ģè¶Ł
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
    POSITIVE LOGITS
    elder
    0.09
    å²©çŁ³
    0.09
     Bou
    0.09
     Taste
    0.09
    cased
    0.08
    åģľçķĻ
    0.08
    ä¸į足
    0.08
     Dude
    0.08
     Pik
    0.08
    æ´ģåĩĢ
    0.08
    Activations Density 0.008%

    No Known Activations