© 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. 7225
    Prev
    Next
    INDEX
    Explanations

    is to

    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
    åIJ¦
    -0.10
    çļĦæĸĩåĮĸ
    -0.09
    åĤ²
    -0.09
    hurst
    -0.09
    强æľīåĬĽçļĦ
    -0.09
    åĵĴ
    -0.09
    æĸĩ书
    -0.08
    rror
    -0.08
    责任å¿ĥ
    -0.08
    Netflix
    -0.08
    POSITIVE LOGITS
    è¦ģæĬĬ
    0.10
     to
    0.10
    çĭ¸
    0.09
     tô
    0.09
    å¸ĮæľĽèĥ½
    0.09
    erc
    0.09
    表æĺİ
    0.09
    赶快
    0.09
    sig
    0.09
    è¦ģ好好
    0.09
    Activations Density 0.128%

    No Known Activations