© 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. 19953
    Prev
    Next
    INDEX
    Explanations

    list item markers or numbers

    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
    çĭ±
    -0.10
    æĬ±
    -0.09
     gener
    -0.09
    çĶ¨å¾®ä¿¡
    -0.09
    æįº
    -0.09
     lap
    -0.09
    髦
    -0.09
    çªĪ
    -0.08
    ä¹¾
    -0.08
    翻身
    -0.08
    POSITIVE LOGITS
    æ±ĩçİĩ
    0.12
    æĸ«
    0.09
    endir
    0.09
    欢è¿İæĤ¨
    0.09
    éĴ¯
    0.09
    peg
    0.09
     Bret
    0.09
    åħijæį¢
    0.08
    åľ°åĿª
    0.08
    å±ł
    0.08
    Activations Density 0.063%

    No Known Activations