© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37777
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ia' or 'an'

    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
    沸
    -0.09
    Creators
    -0.09
    åĩº
    -0.08
    nod
    -0.08
    ä¸ĩåIJį
    -0.08
    .Assertions
    -0.08
    brook
    -0.08
    沸èħ¾
    -0.08
    纷
    -0.08
    ynamo
    -0.08
    POSITIVE LOGITS
    亡
    0.10
    çļĦè¿ĽæŃ¥
    0.09
    å¬ĸ
    0.09
    èĺ¸
    0.09
    åħ±åIJĮåĬªåĬĽ
    0.09
    lag
    0.09
    å¤ĸåĽ½è¯Ń
    0.08
    éĩįè¦ģåİŁåĽł
    0.08
    çľ¼éĥ¨
    0.08
    rips
    0.08
    Activations Density 0.045%

    No Known Activations