© 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. 2052
    Prev
    Next
    INDEX
    Explanations

    nominations and awards

    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
    олов
    -0.09
    åĵį
    -0.09
    èģĮæĿĥ
    -0.08
    è¯Ħ级
    -0.08
    颧
    -0.08
    履约
    -0.08
    _kw
    -0.08
     rif
    -0.08
    æĹ¥æĬ¥è®°èĢħ
    -0.08
    ç»ĺåĪ¶
    -0.08
    POSITIVE LOGITS
    纵åIJij
    0.10
    åĵī
    0.10
    åģ¥
    0.10
    _dual
    0.09
    ä¸ļçķĮ
    0.09
    横åIJij
    0.09
    åĽŀ头çľĭ
    0.09
    å½Ĵ纳
    0.09
    æĶ¹æŃ£
    0.09
    åŁİåİ¿
    0.09
    Activations Density 0.092%

    No Known Activations