© 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. 7757
    Prev
    Next
    INDEX
    Explanations

    inaugural edition, season, or event

    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
    ening
    -0.09
    archy
    -0.08
    æĢĤ
    -0.08
    locals
    -0.08
    èĶ¼
    -0.08
    boo
    -0.08
    èĸĦ
    -0.08
    æľ¬ç½ij
    -0.08
     reservoir
    -0.08
     older
    -0.08
    POSITIVE LOGITS
    idad
    0.10
    dehyde
    0.10
    ä¹ĭä½ľ
    0.09
    æ¶ķ
    0.09
    çĤ³
    0.09
    idal
    0.09
    æĢ§çļĦ
    0.09
    ãĤĤãģ®ãģ®
    0.09
    ocity
    0.09
    æ¶ī
    0.09
    Activations Density 0.005%

    No Known Activations