© 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. 18172
    Prev
    Next
    INDEX
    Explanations

    cyber security and vulnerabilities

    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
    åĹª
    -0.09
    è¿ĩåī©
    -0.09
     Conditioning
    -0.09
    å¼Ģåĩº
    -0.09
    æijĬ
    -0.09
    adic
    -0.09
    æĪijä¸Ģ缴
    -0.09
    ogue
    -0.09
    åĨħåľ°
    -0.08
    æĹ¶æľº
    -0.08
    POSITIVE LOGITS
     cybersecurity
    0.10
    rail
    0.09
    çħ§æł·
    0.08
    contra
    0.08
    ansa
    0.08
    edom
    0.08
     scare
    0.08
    ä¿¡æģ¯å®īåħ¨
    0.08
    æľ¨è´¨
    0.08
    èĭİ
    0.08
    Activations Density 0.097%

    No Known Activations