© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8458
    Prev
    Next
    INDEX
    Explanations

    sentence construction

    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
    éĿ¢åŃIJ
    -0.10
    orting
    -0.09
    moves
    -0.09
    纯粹
    -0.09
    éĢ¢
    -0.09
    çľĭä¸įåĪ°
    -0.09
    CharCode
    -0.08
    uai
    -0.08
    ymbol
    -0.08
    à¹Ĥà¸Ľ
    -0.08
    POSITIVE LOGITS
    åı¥åŃIJ
    0.21
     sentence
    0.18
    åı¥
    0.17
     sentences
    0.17
    è¿Ļåı¥è¯Ŀ
    0.16
    Sentence
    0.15
    ä¸Ģåı¥è¯Ŀ
    0.15
    sentence
    0.15
    åı¥è¯Ŀ
    0.14
    ä¸Ģåı¥
    0.13
    Activations Density 0.071%

    No Known Activations