© 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. 52738
    Prev
    Next
    INDEX
    Explanations

    security vulnerability CVE

    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
    åįĬå²Ľ
    -0.12
    åĬłéĩį
    -0.11
    è¹¼
    -0.10
    éªģ
    -0.09
    为ä¹ĭ
    -0.09
    áĥ©
    -0.09
    olds
    -0.09
    æĻĥ
    -0.09
    çķ´
    -0.09
    éĤ»éĩĮ
    -0.09
    POSITIVE LOGITS
    æ¼ıæ´ŀ
    0.14
     vulnerability
    0.12
     vulner
    0.11
     vulnerabilities
    0.11
    éļIJæĤ£
    0.11
    CVE
    0.10
     Vulner
    0.10
    èĸĦå¼±
    0.10
    åį±
    0.09
    æĶ»åĩ»
    0.09
    Activations Density 0.131%

    No Known Activations