© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10556
    Prev
    Next
    INDEX
    Explanations

    size of groups or places

    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
    ighth
    -0.09
     McCoy
    -0.09
    ibal
    -0.09
    驹
    -0.09
    æ³ķå®ļ
    -0.08
    TERS
    -0.08
    çıº
    -0.08
    涣
    -0.08
    åIJĮåŁİ
    -0.08
    Sdk
    -0.08
    POSITIVE LOGITS
     peek
    0.09
    ä¸įéĶĻçļĦ
    0.08
    -fat
    0.08
    ä½Ĩæĺ¯åľ¨
    0.08
    ä¸Ŀ
    0.08
    ish
    0.08
    åį´è¢«
    0.08
     Tiny
    0.08
    ä¸İä¼Ĺ
    0.08
    ament
    0.08
    Activations Density 0.020%

    No Known Activations