© 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. 9538
    Prev
    Next
    INDEX
    Explanations

    big picture

    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
    çıĬçijļ
    -0.10
    ogh
    -0.10
     Cham
    -0.09
    (cors
    -0.08
    æ²»
    -0.08
    æļij
    -0.08
     Feather
    -0.08
     spoken
    -0.08
    itr
    -0.08
    æĩ¦
    -0.08
    POSITIVE LOGITS
    大å±Ģ
    0.19
    个åĪ«
    0.11
    æĺİæľĹ
    0.11
    åħ¨å±Ģ
    0.11
    广éĺĶçļĦ
    0.11
     mù
    0.10
    çľ¼åīįçļĦ
    0.10
    广éĺĶ
    0.10
    è§Ĩéĩİ
    0.10
    _PICTURE
    0.09
    Activations Density 0.050%

    No Known Activations