© 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. 8022
    Prev
    Next
    INDEX
    Explanations

    screenshot

    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
    ständ
    -0.10
    stead
    -0.10
    çĪ·
    -0.09
    emble
    -0.09
    heart
    -0.09
    ussian
    -0.08
    icky
    -0.08
    andbox
    -0.08
    urga
    -0.08
    avier
    -0.08
    POSITIVE LOGITS
    ãĤĭãĤĤãģ®
    0.10
    äºĨæĪijçļĦ
    0.10
    ting
    0.09
     ÑĤого
    0.09
     Former
    0.09
    å¿«ä¸ī
    0.09
    elles
    0.09
     Gast
    0.08
    IEL
    0.08
    acular
    0.08
    Activations Density 0.016%

    No Known Activations