© 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. 7772
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    è¿Ļ两ç§į
    -0.09
    ä¸İåIJ¦
    -0.09
    ye
    -0.08
    rosso
    -0.08
    åĽĽç§į
    -0.08
    滢
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    yer
    -0.08
    æľīåIJį
    -0.08
    isoft
    -0.08
    POSITIVE LOGITS
    /or
    0.13
    ifice
    0.10
    phans
    0.10
    çĶļèĩ³
    0.09
    acular
    0.09
    éĩĩçŁ¿çŃī
    0.09
    REA
    0.09
    пÑĢÑı
    0.09
    æħij
    0.09
    бли
    0.09
    Activations Density 0.243%

    No Known Activations