© 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. 30001
    Prev
    Next
    INDEX
    Explanations

    topics discussed

    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
     Kron
    -0.09
    æĪı
    -0.09
    åħij
    -0.09
    åı·
    -0.08
    èĮĥ
    -0.08
    ãĥ¼ãĥ«
    -0.08
    çľ¼ä¸Ń
    -0.08
     Lore
    -0.08
     ther
    -0.07
    è·»
    -0.07
    POSITIVE LOGITS
     Topics
    0.14
     topics
    0.14
    Topics
    0.13
    çļĦè¯Ŀé¢ĺ
    0.13
    topics
    0.12
    çļĦ主é¢ĺ
    0.12
     topic
    0.11
    ÙħÙĪا
    0.11
    (topic
    0.11
    è¯Ŀé¢ĺ
    0.10
    Activations Density 0.090%

    No Known Activations