© 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. 30482
    Prev
    Next
    INDEX
    Explanations

    money, cost, expense

    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
    illes
    -0.10
    -clock
    -0.09
    Clock
    -0.09
    _CID
    -0.09
     اÙĦÙĥÙħ
    -0.09
    CDATA
    -0.09
     Clock
    -0.09
    INGER
    -0.09
    forum
    -0.09
    éric
    -0.09
    POSITIVE LOGITS
    忽
    0.10
    åIJİèĢħ
    0.09
    æľºç¥¨
    0.09
    å¸Ľ
    0.09
    åĴĮæĬĢæľ¯
    0.09
    åħ«åį¦
    0.09
    æĮģ
    0.09
    åıĪ好
    0.09
    _dual
    0.08
    é©¿
    0.08
    Activations Density 0.243%

    No Known Activations