© 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. 7688
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and structures

    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
    ned
    -0.10
    edList
    -0.09
    æģ°
    -0.09
    åĬŀæ³ķ
    -0.09
    人éĹ´
    -0.08
    çĦ¶æĺ¯
    -0.08
    é¡
    -0.08
    è¡£
    -0.08
    lu
    -0.08
    Qualified
    -0.08
    POSITIVE LOGITS
    éĺ²æ²»
    0.10
    åĵ¨
    0.10
    вол
    0.09
    活泼
    0.09
    endar
    0.09
    èݽ
    0.09
    横
    0.09
    çĹĶ
    0.09
    éĢ¡
    0.09
    åĩ¶
    0.08
    Activations Density 0.084%

    No Known Activations