© 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. 27870
    Prev
    Next
    INDEX
    Explanations

    let 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
    inbox
    -0.09
    å°±è¿ij
    -0.09
    ä¹IJæĦı
    -0.09
    ãĢħ
    -0.09
    illion
    -0.08
     led
    -0.08
    屯
    -0.08
    /exp
    -0.08
    åİŁæľī
    -0.08
    ä¸įåıĹ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.12
    é«ĺ空
    0.10
    ä»»ä½ķ人
    0.10
    awah
    0.10
    åį³ä½¿æĺ¯
    0.09
     EVER
    0.09
    çŀij
    0.09
    åĵªæĢķæĺ¯
    0.09
    åį³ä½¿
    0.09
    tabl
    0.08
    Activations Density 0.015%

    No Known Activations