© 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. 54619
    Prev
    Next
    INDEX
    Explanations

    proper nouns after 'of'

    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
    ÙĦاÙģ
    -0.11
    iban
    -0.10
    æĭĺ
    -0.09
     oppos
    -0.09
    å¹´åĨħ
    -0.09
    burger
    -0.08
    æĤĦ
    -0.08
    åľ¨è·¯ä¸Ĭ
    -0.08
    æİī
    -0.08
    è¿ĻäºĽä¸ľè¥¿
    -0.08
    POSITIVE LOGITS
    strate
    0.09
    ãĥ¢ãĥ³
    0.09
    uby
    0.08
    ForResource
    0.08
    uong
    0.08
     Reeves
    0.08
    rys
    0.08
    çĦī
    0.08
     the
    0.07
     Johannes
    0.07
    Activations Density 0.028%

    No Known Activations