© 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. 20834
    Prev
    Next
    INDEX
    Explanations

    Australian rules football

    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
    åĽŀåĽ½
    -0.10
    neau
    -0.10
    å¼Ħ
    -0.09
    éĢĬ
    -0.09
    æĹħ
    -0.09
    赶
    -0.09
    强çĥĪ
    -0.09
    åĥĸ
    -0.09
    éĹŃ
    -0.08
    .EventQueue
    -0.08
    POSITIVE LOGITS
    è¿ľæĸ¹
    0.09
    ster
    0.08
    çħĬ
    0.08
    election
    0.08
    åĬ¿
    0.08
    以人为
    0.08
     fb
    0.08
    åħ¬çĽĬ
    0.08
    éĹľéįµ
    0.08
    Confirmation
    0.08
    Activations Density 0.040%

    No Known Activations