© 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. 21326
    Prev
    Next
    INDEX
    Explanations

    Cain, Riverdale, Alcatraz, HanselGretel

    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
    inan
    -0.10
    вид
    -0.10
    éĴ»çłĶ
    -0.10
    ä¸Ńåľº
    -0.10
    对ä»ĸ们
    -0.09
    好çľĭ
    -0.09
    èĬĺ
    -0.09
    亥
    -0.09
    é£İåħī
    -0.09
     Ree
    -0.09
    POSITIVE LOGITS
     sus
    0.08
    æ»ĭ
    0.08
    宫
    0.08
    bez
    0.08
    zig
    0.07
    æĽ°
    0.07
    身ä¸Ĭ
    0.07
    èĢ¤
    0.07
    ç»
    0.07
    ìĵ´
    0.07
    Activations Density 0.055%

    No Known Activations