© 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. 21770
    Prev
    Next
    INDEX
    Explanations

    victims, families, tragic events, and support

    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
     sigu
    -0.08
    1
    -0.08
    æŁIJ
    -0.07
     scrim
    -0.07
    ãģĤãĤĬãģĮ
    -0.07
    æ°Ķ温
    -0.07
    ((_
    -0.07
    4
    -0.07
    tics
    -0.07
     suff
    -0.07
    POSITIVE LOGITS
    æĤ²ä¼¤
    0.12
    伤亡
    0.11
    尽快
    0.11
    æŃ¤æ¬¡
    0.11
    åijĬè¯ī大家
    0.10
    è¿Ļ次
    0.10
    æĹ©æĹ¥
    0.10
    éĢĻ次
    0.10
    ¹Ħ
    0.10
    é¦ĸè½®
    0.10
    Activations Density 0.040%

    No Known Activations