© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38845
    Prev
    Next
    INDEX
    Explanations

    -er endings

    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
    翳
    -0.09
    را
    -0.09
     æĬ
    -0.08
     Garland
    -0.08
    å½ķ
    -0.08
    ãģĹãģ¾
    -0.08
    bulk
    -0.08
     strconv
    -0.08
    =rand
    -0.08
    åŃ£
    -0.08
    POSITIVE LOGITS
    们
    0.10
    éĤij
    0.09
    å¾Īæ¼Ĥ亮
    0.09
    èłķ
    0.09
    åĢij
    0.08
    ponder
    0.08
    产ä¸ļéĵ¾
    0.08
    ä¹Łæĺ¯ä¸Ģ个
    0.08
    ces
    0.08
    æĺ¯ä¸Ģéĥ¨
    0.08
    Activations Density 0.063%

    No Known Activations