© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51132
    Prev
    Next
    INDEX
    Explanations

    United States of America

    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
    iste
    -0.10
    é©°
    -0.10
    izzer
    -0.09
    æĶĢ
    -0.09
    osti
    -0.09
    enco
    -0.09
    ä¾£
    -0.09
    å¼Ľ
    -0.09
    æłª
    -0.09
    IVA
    -0.09
    POSITIVE LOGITS
    æ³ĵ
    0.08
    åĪ°åºķæĺ¯
    0.08
    åħij
    0.08
    imit
    0.08
    èģª
    0.08
    èIJĿåįľ
    0.07
    çİĭåħĪçĶŁ
    0.07
    inals
    0.07
    plex
    0.07
    çī¹åĪ«æĺ¯
    0.07
    Activations Density 0.302%

    No Known Activations