© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    security breaches and theft

    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
    å¾¹
    -0.10
    å®ĺæĸ¹å¾®ä¿¡
    -0.09
    æĢ¨
    -0.09
    è¯ħ
    -0.09
    ãĤīãģĦ
    -0.08
    æĿĢäºĨ
    -0.08
    å½»åºķ
    -0.08
    æľīæ¯Ĵ
    -0.08
    ä½ľèĢħæľ¬äºº
    -0.08
    è¯Ľ
    -0.08
    POSITIVE LOGITS
    çĽĹ
    0.12
    è§Ĭ
    0.12
    çĽĹçªĥ
    0.11
    è¯ķåĽ¾
    0.11
    å°§
    0.10
    ä¼ģåĽ¾
    0.10
    å¤ĸéĥ¨
    0.10
     attempts
    0.10
    .openapi
    0.10
     Attempts
    0.09
    Activations Density 0.109%

    No Known Activations