© 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. 9179
    Prev
    Next
    INDEX
    Explanations

    unanimous vote or opinion

    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
    人èĦī
    -0.09
    pulse
    -0.09
    rame
    -0.09
    ves
    -0.09
    pus
    -0.08
    inha
    -0.08
     humble
    -0.08
     Olsen
    -0.08
     urn
    -0.08
    eus
    -0.08
    POSITIVE LOGITS
    ecom
    0.11
    é£ķ
    0.10
    å¸Ń
    0.10
    emente
    0.09
    uly
    0.09
    reds
    0.09
     تÙĤ
    0.09
    æĦıè§ģ
    0.09
    ä¸Ģèĩ´
    0.08
    ltra
    0.08
    Activations Density 0.007%

    No Known Activations