© 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. 20702
    Prev
    Next
    INDEX
    Explanations

    clothing items

    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
    orsche
    -0.10
    ira
    -0.09
    ively
    -0.09
    å¾ģæ±Ĥ
    -0.09
    æīĭä¸Ń
    -0.09
    flat
    -0.08
    çģ«çĥ§
    -0.08
    è¦ļ
    -0.08
    éĴ°
    -0.08
    åĿĩåĮĢ
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.09
    Ñħо
    0.09
    uder
    0.08
    æĪIJé¾Ļ
    0.08
    èĬ±æł·
    0.08
    æĭįæĭį
    0.08
    nist
    0.08
     Gast
    0.08
    enta
    0.08
    \xb
    0.08
    Activations Density 0.005%

    No Known Activations