© 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. 8578
    Prev
    Next
    INDEX
    Explanations

    asserts that

    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
    åħĴ
    -0.10
    åĦ¿
    -0.10
    æķŀ
    -0.09
    æĭĻ
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    çļĦä¸Ģ款
    -0.08
     Meredith
    -0.08
    ãĥľãĥ¼
    -0.08
    纰
    -0.08
    åį«
    -0.08
    POSITIVE LOGITS
    edly
    0.13
    MENT
    0.11
    ä¸ĢåĪĩéĥ½æĺ¯
    0.11
    ment
    0.11
     rằng
    0.10
    MENTS
    0.10
    forth
    0.10
    rians
    0.09
    éļħ
    0.09
    åĩłåIJį
    0.09
    Activations Density 0.011%

    No Known Activations