© 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. 52440
    Prev
    Next
    INDEX
    Explanations

    inventory management and tracking

    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
    ðŁı»
    -0.10
     воÑĤ
    -0.09
    ston
    -0.09
    beck
    -0.09
    AxisSize
    -0.09
     вÑģего
    -0.09
    ãģ£ãģ±
    -0.09
    ðŁı¼
    -0.09
    æł·çļĦ
    -0.09
    ified
    -0.09
    POSITIVE LOGITS
    л
    0.10
    éģķãģĦ
    0.09
    lı
    0.09
    lu
    0.09
    大声
    0.08
    eer
    0.08
    å¿ĥåºķ
    0.08
    .ItemStack
    0.08
    izon
    0.08
    ç¯Ŀ
    0.08
    Activations Density 0.009%

    No Known Activations