© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52187
    Prev
    Next
    INDEX
    Explanations

    quantities or durations

    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
    楣
    -0.09
    emann
    -0.09
    .raise
    -0.08
    æİ¥åıĹäºĨ
    -0.08
    湫
    -0.08
    quartered
    -0.08
    æĭŃ
    -0.08
    æīįç®Ĺ
    -0.08
    ronic
    -0.08
     Russo
    -0.08
    POSITIVE LOGITS
     hundreds
    0.13
    æķ°çĻ¾
    0.13
    åĩłåįģ
    0.12
    ä¹ĥèĩ³
    0.12
    åĩłåįĥ
    0.12
    æķ°åįģ
    0.11
    åĩłçĻ¾
    0.11
    ä¸ĬçĻ¾
    0.10
    èĢĥåľº
    0.10
     ÑģоÑĤ
    0.10
    Activations Density 0.132%

    No Known Activations