© 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. 8239
    Prev
    Next
    INDEX
    Explanations

    FDIC insured money, protected, welcome

    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
    忤
    -0.10
    ools
    -0.08
    atsu
    -0.08
    åĬŁè¯¾
    -0.08
    uls
    -0.08
    ÑĢÑĥд
    -0.08
    eld
    -0.08
     har
    -0.08
    大åѦæ¯ķä¸ļ
    -0.08
    çĦķåıij
    -0.08
    POSITIVE LOGITS
    çĩİ
    0.11
    åIJĪæ³ķæĿĥçĽĬ
    0.11
    ä¿Ŀéļľ
    0.10
    åĨ»ç»ĵ
    0.10
    ä¿ĿæĬ¤
    0.10
    ä¿ĿèŃ·
    0.10
    è¦Ĩ
    0.09
    æĭİ
    0.09
    ç´¢èµĶ
    0.09
    èł¹
    0.09
    Activations Density 0.040%

    No Known Activations