© 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. 4939
    Prev
    Next
    INDEX
    Explanations

    after someone or something

    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
    以åıĬåħ¶ä»ĸ
    -0.11
    åĨįæĿ¥
    -0.10
    æ®Ĩ
    -0.10
    ä¸ĭåİ»
    -0.10
    ä¹Łåı¯èĥ½
    -0.09
    igator
    -0.09
    ейÑĩаÑģ
    -0.09
    ç»Ŀ
    -0.09
     ÙĦدÙĬÙĥ
    -0.09
    pret
    -0.09
    POSITIVE LOGITS
    èĭĩ
    0.10
    å®ĥæĺ¯
    0.09
    uml
    0.09
    -sales
    0.08
    å±¥èģĮ
    0.08
    éļIJ
    0.08
    èĢģ头
    0.08
    noon
    0.08
    åıijæĸĩ
    0.08
    åħ´èµ·
    0.08
    Activations Density 0.059%

    No Known Activations