© 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. 52026
    Prev
    Next
    INDEX
    Explanations

    possessive and contracted apostrophes

    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
    ’s
    -0.11
    çļĦåĽłç´ł
    -0.10
    's
    -0.09
    ä¸Ģç¢Ĺ
    -0.09
    less
    -0.09
    çļĦéĩįçĤ¹
    -0.09
    çļĦåıijå±ķ
    -0.08
    çļĦ认è¯Ĩ
    -0.08
    iej
    -0.08
    çļĦè§ĤçĤ¹
    -0.08
    POSITIVE LOGITS
    âĶŀ
    0.10
    sing
    0.10
    ieur
    0.10
    /downloads
    0.10
    chnitt
    0.09
    chaft
    0.09
    quared
    0.09
    .instances
    0.09
    invoke
    0.09
     behalf
    0.09
    Activations Density 0.207%

    No Known Activations