© 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. 51441
    Prev
    Next
    INDEX
    Explanations

    individuals and entities

    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
    åĬ¿
    -0.10
    åĵij
    -0.09
    æī¬
    -0.09
    çłĶ究ä¸Ńå¿ĥ
    -0.09
     Yue
    -0.09
    urse
    -0.09
    æ£ł
    -0.08
    龸éģĵ
    -0.08
    æ½ľæ°´
    -0.08
    ÙĤت
    -0.08
    POSITIVE LOGITS
    è¿Ļ个人
    0.12
    人çī©
    0.11
    人éĢī
    0.11
    äººæł¼
    0.10
    æŃ¤äºº
    0.10
    ä¹ĭ人
    0.10
    人æīį
    0.09
     person
    0.09
    å§ĵåIJį
    0.09
     Persona
    0.09
    Activations Density 0.187%

    No Known Activations