© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8052
    Prev
    Next
    INDEX
    Explanations

    company types (Corporation, PLC, Corp)

    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
    andon
    -0.09
     aff
    -0.09
    aver
    -0.09
    è¶Ĭè¿ĩ
    -0.09
     Ih
    -0.09
    妹妹
    -0.08
    ç²½åŃIJ
    -0.08
    éĢŁåº¦å¿«
    -0.08
    unfold
    -0.08
    icie
    -0.08
    POSITIVE LOGITS
    ä½ĵéĩį
    0.09
    èĬ¸
    0.09
    åĮĸ
    0.09
    æŃª
    0.09
    weigh
    0.08
    .Scroll
    0.08
     crack
    0.08
    ikip
    0.08
    ini
    0.08
    ä¸į太
    0.08
    Activations Density 0.063%

    No Known Activations