© 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. 36711
    Prev
    Next
    INDEX
    Explanations

    comparative relationships

    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
    èĪ«
    -0.09
    åģļçļĦ
    -0.09
    isky
    -0.09
    esture
    -0.09
    vidence
    -0.08
    éŃĶ鬼
    -0.08
    麾
    -0.08
    rights
    -0.08
    åħ¼
    -0.08
    æŀģ度
    -0.08
    POSITIVE LOGITS
    沦
    0.11
    åłª
    0.10
    аÑħ
    0.08
     Ritch
    0.08
    -ignore
    0.08
    ä¸įéĹ´æĸŃ
    0.08
     Nag
    0.08
    NE
    0.08
     pitched
    0.08
    ä¸Ģåı·
    0.08
    Activations Density 0.160%

    No Known Activations