© 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. 31570
    Prev
    Next
    INDEX
    Explanations

    language translation context

    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
    åľ¨ä¹İ
    -0.10
    çĶ»åį·
    -0.08
     Phelps
    -0.08
    иÑĤелÑĮно
    -0.08
    æ¼Ĥæµģ
    -0.08
    bows
    -0.08
    åħijçİ°
    -0.08
    omy
    -0.08
    äºĭåħ³
    -0.08
    ASA
    -0.08
    POSITIVE LOGITS
    éģĶ
    0.11
    æ°
    0.10
    çĪ±å¥½èĢħ
    0.09
    лов
    0.09
    elder
    0.09
     Hir
    0.09
    对éĿ¢
    0.08
    è¿Ļçīĩ
    0.08
    å®ŀæĸ½ç»ĨåĪĻ
    0.08
    ates
    0.08
    Activations Density 0.102%

    No Known Activations