© 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. 51526
    Prev
    Next
    INDEX
    Explanations

    comma followed by pronoun

    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
    çļĦ人æĿ¥è¯´
    -0.13
    quire
    -0.10
    äºı
    -0.10
    æĪijå½ĵæŶ
    -0.10
    èĢĮè¨Ģ
    -0.10
    çļĦåīįæıIJä¸ĭ
    -0.10
    ä¾Ĩ說
    -0.09
    æĿ¥è¯´
    -0.09
    æĿ¥è®²
    -0.09
    èµĦæºIJä¼ĺåĬ¿
    -0.09
    POSITIVE LOGITS
    åħ¶
    0.11
    æĥ³åĪ°
    0.10
    说æĺİ
    0.10
    æīįåıijçİ°
    0.09
    å¿ħ
    0.09
    說æĺİ
    0.09
     Ñģвоего
    0.08
    æĦŁè§ī
    0.08
    å°±æĬĬ
    0.08
     swims
    0.08
    Activations Density 0.102%

    No Known Activations