© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5128
    Prev
    Next
    INDEX
    Explanations

    race, form, conditions, new

    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
    æ±ĩæĬ¥
    -0.10
    è¿Ķ
    -0.09
    athom
    -0.08
    åĹ£
    -0.08
    é¦Ī
    -0.08
    æľį
    -0.08
    avage
    -0.08
    åĪĥ
    -0.08
    à¸Ńà¸Ļ
    -0.08
     surf
    -0.08
    POSITIVE LOGITS
    abl
    0.10
    frei
    0.09
    éĢīæīĭ
    0.09
     поп
    0.09
    WordPress
    0.08
    人人éĥ½
    0.08
    æĶ¾ç¼ĵ
    0.08
    äººåľ¨
    0.08
    æķ¬ä¸ļ
    0.08
    两级
    0.08
    Activations Density 0.025%

    No Known Activations