© 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. 21273
    Prev
    Next
    INDEX
    Explanations

    to the west/east/south/left

    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
    ä¸ŃéĢĶ
    -0.10
    åħ¥åĽŃ
    -0.10
    flate
    -0.09
    è¿ľæĻ¯
    -0.09
    è§Į
    -0.09
    åģľæ»ŀ
    -0.09
    èĨı
    -0.09
    å¦ĤæľŁ
    -0.08
    å±Ĥåĩº
    -0.08
     Mitchell
    -0.08
    POSITIVE LOGITS
    å¥Ĺ
    0.12
    两侧
    0.10
    ä¸Ģè¾¹
    0.10
    uda
    0.09
    /vendors
    0.09
    pon
    0.08
    éī´
    0.08
    ТÐĺ
    0.08
    arial
    0.08
    åįµ
    0.08
    Activations Density 0.070%

    No Known Activations