© 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. 21993
    Prev
    Next
    INDEX
    Explanations

    local places and services

    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
    è¿Ļè¾ĪåŃIJ
    -0.09
     dock
    -0.08
    çĵľ
    -0.08
    หลวà¸ĩ
    -0.08
    æıIJæĮ¯
    -0.08
    åħ®
    -0.08
    Ñģлед
    -0.08
     Loft
    -0.08
    æĿ³
    -0.08
    çįIJ
    -0.08
    POSITIVE LOGITS
    ç¼ĺåĪĨ
    0.09
    å¼ĢæĶ¾å¼ı
    0.09
    -redux
    0.09
    ounty
    0.09
    æ°§æ°Ķ
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    åĸľçĪ±
    0.09
    idad
    0.09
    /Internal
    0.09
    å·²ç»ıæľī
    0.09
    Activations Density 0.013%

    No Known Activations