© 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. 37385
    Prev
    Next
    INDEX
    Explanations

    necklace and jewelry

    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
    olia
    -0.10
    裱
    -0.09
    æ¤į
    -0.09
    ÙĪØ·
    -0.09
    PROP
    -0.09
     Ñĥзн
    -0.09
    aira
    -0.09
    åħ³éŨ
    -0.08
    çħ¦
    -0.08
    æĬĺåıł
    -0.08
    POSITIVE LOGITS
    项éĵ¾
    0.14
    æĮĤåľ¨
    0.11
     necklace
    0.11
    佩æĪ´
    0.11
    佩
    0.11
    èĥ¸åīį
    0.10
    æĮĤ
    0.10
    avigator
    0.10
     neckline
    0.09
    æĮĤçīĮ
    0.09
    Activations Density 0.049%

    No Known Activations