© 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. 29990
    Prev
    Next
    INDEX
    Explanations

    dominance or supremacy

    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
    å¥ĩ迹
    -0.10
    ведение
    -0.09
    é½IJåħ¨
    -0.09
    itting
    -0.09
    ÙĦÙĥ
    -0.08
    alia
    -0.08
    acking
    -0.08
    åģ¶
    -0.08
    yc
    -0.08
    红楼
    -0.08
    POSITIVE LOGITS
    éľīç´ł
    0.10
    çĦī
    0.09
    è¾Ľ
    0.09
    åľ°ä½į
    0.09
    htar
    0.09
    mind
    0.08
    nah
    0.08
    Ñģкоп
    0.08
    jun
    0.08
    çĤ¹çĤ¹å¤´
    0.08
    Activations Density 0.008%

    No Known Activations