© 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. 8174
    Prev
    Next
    INDEX
    Explanations

    "this" followed by noun/verb

    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
    æĸ°å½¢åĬ¿
    -0.08
    åħĪ导
    -0.08
    ogle
    -0.08
    å¤ĩæ¡Ī
    -0.08
    æŃĥ
    -0.08
    Finder
    -0.08
    äºĭåĦ¿
    -0.08
    å¸ĤåľºéľĢæ±Ĥ
    -0.08
    ade
    -0.07
    _calls
    -0.07
    POSITIVE LOGITS
    åĮħ容
    0.10
     пÑĢож
    0.09
     Ag
    0.09
    inclusive
    0.09
    suming
    0.09
    æĺ¯ä¸ª
    0.09
    éł
    0.09
     inclusive
    0.09
     данного
    0.09
    åħ¼åħ·
    0.09
    Activations Density 0.134%

    No Known Activations