© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37715
    Prev
    Next
    INDEX
    Explanations

    continues or will continue

    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
    çĿ¨
    -0.09
    ymbol
    -0.09
    人士
    -0.08
    ONT
    -0.08
    è¦ģçŁ¥éģĵ
    -0.08
    è¯Ŀé¢ĺ
    -0.08
    ronic
    -0.08
    ont
    -0.08
    Subject
    -0.08
    çĮ
    -0.08
    POSITIVE LOGITS
    å°Ĩ继ç»Ń
    0.14
    继ç»Ń
    0.12
    ãģĵãĤĮãģĭãĤī
    0.12
    å°ĨæĿ¥
    0.10
    ä»ĬåIJİ
    0.10
    ä»įåľ¨
    0.10
    ä»įå°Ĩ
    0.10
     continues
    0.10
    åį³å°Ĩ
    0.10
     continue
    0.10
    Activations Density 0.062%

    No Known Activations