© 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. 7494
    Prev
    Next
    INDEX
    Explanations

    aqua, turquoise, cyan, indigo

    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
    çĥŁçģ«
    -0.09
    æ¯ĶæĪij
    -0.08
    incer
    -0.08
    æłĩ
    -0.08
    è¹
    -0.08
    æĸ°åŁİ
    -0.08
    unders
    -0.08
    0
    -0.08
    æ·¡
    -0.08
     fired
    -0.07
    POSITIVE LOGITS
    ç»ıèIJ¥èĮĥåĽ´
    0.11
    æ³ķå¾ĭè§Ħå®ļ
    0.10
    èļĵ
    0.10
    RequestParam
    0.10
    åŀļ
    0.09
     depths
    0.09
    æĿ¥çĶµ
    0.09
    æĭ¾
    0.09
    ephy
    0.09
     Formal
    0.09
    Activations Density 0.047%

    No Known Activations