© 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. 26533
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency and blockchain projects

    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
    æķĪèĥ½
    -0.10
     Burl
    -0.09
    æĮŁ
    -0.09
    å¾Ħ
    -0.08
    åįĸåľº
    -0.08
    tablet
    -0.08
    她们
    -0.08
    ä¸ĭçıŃ
    -0.08
    å®ŀä¹łçĶŁ
    -0.08
    æĻ¡
    -0.08
    POSITIVE LOGITS
     Ethereum
    0.12
    éĵ¾
    0.11
    staking
    0.10
     ETH
    0.10
    éĴ±åĮħ
    0.10
     vest
    0.10
    ETH
    0.09
    交æĺĵæīĢ
    0.09
    代
    0.09
    chain
    0.09
    Activations Density 0.414%

    No Known Activations