© 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. 51855
    Prev
    Next
    INDEX
    Explanations

    instrumental in

    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
    éĤ£ä¹Īå¤ļ
    -0.09
    itude
    -0.09
    å®ŀäºĭæ±Ĥæĺ¯
    -0.08
    çīĪæĿĥ声æĺİ
    -0.08
    åģļçļĦäºĭæĥħ
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    agas
    -0.08
    æĮŁ
    -0.08
    ç²¾
    -0.08
    æīĢéľĢè¦ģ
    -0.08
    POSITIVE LOGITS
     crucial
    0.14
    èĩ³åħ³éĩįè¦ģ
    0.13
    èĩ³åħ³
    0.12
    éĿŀ常éĩįè¦ģ
    0.11
     vital
    0.11
    éĩįè¦ģçļĦ
    0.10
    éĩįè¦ģä½ľçĶ¨
    0.10
     важ
    0.10
    åħ³éĶ®
    0.10
    สำà¸Ħ
    0.10
    Activations Density 0.049%

    No Known Activations