© 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. 27484
    Prev
    Next
    INDEX
    Explanations

    actors and artists

    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
     pod
    -0.09
    ither
    -0.09
    alem
    -0.09
     verst
    -0.08
    ä»Ĭ天çļĦ
    -0.08
     POD
    -0.08
    eworld
    -0.08
    andin
    -0.08
    asel
    -0.08
    ITE
    -0.08
    POSITIVE LOGITS
    åħ±äº§åħļåijĺ
    0.09
    oner
    0.09
    å¿ĥ头
    0.08
    à¹Ĥà¸ŀ
    0.08
    Invoker
    0.08
    ç§ijæķĻ
    0.07
    è¯Ŀ说
    0.07
    üler
    0.07
    忧èĻij
    0.07
    (?
    0.07
    Activations Density 1.186%

    No Known Activations