© 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. 30449
    Prev
    Next
    INDEX
    Explanations

    many or several followed by plural nouns

    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
    utow
    -0.09
    erb
    -0.09
    ä¸ĩä¸Ģ
    -0.08
    ÑıÑĤ
    -0.08
    ç»Ļä»ĸ们
    -0.08
    uts
    -0.08
    edic
    -0.08
    бе
    -0.08
    åIJij社ä¼ļ
    -0.08
    SPAN
    -0.08
    POSITIVE LOGITS
    å¾Īéĩįè¦ģ
    0.10
    åĩĨ
    0.09
    ç±»åŀĭçļĦ
    0.09
    /all
    0.09
    éĩįè¦ģçļĦ
    0.09
    org
    0.09
    åħ³éĶ®æĬĢæľ¯
    0.09
    azes
    0.09
    -many
    0.09
     notable
    0.08
    Activations Density 0.090%

    No Known Activations