© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39404
    Prev
    Next
    INDEX
    Explanations

    cyber warfare, hacking, hacker

    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
    æĥ¨
    -0.10
    åĢ
    -0.09
    çĭ¼
    -0.08
    楼ä¸Ĭ
    -0.08
    åĩºçīĪ社
    -0.08
    olem
    -0.08
    åIJ«
    -0.08
    mü
    -0.08
    æī¿æİ¥
    -0.08
    ugo
    -0.08
    POSITIVE LOGITS
    é»ij客
    0.16
    æĶ»
    0.13
     hacker
    0.12
     hackers
    0.12
     hacking
    0.11
    çĹħæ¯Ĵ
    0.11
    å°ıå¾®
    0.11
    çݰ身
    0.10
    æĶ»åĩ»
    0.10
    åĦ¿
    0.10
    Activations Density 0.106%

    No Known Activations