© 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. 10139
    Prev
    Next
    INDEX
    Explanations

    cyberattacks and malicious attacks

    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
    çŃ®
    -0.09
    塬
    -0.09
    alin
    -0.09
    ä¸Ĭä¸ĭ
    -0.09
    éģº
    -0.09
    åĬĪ
    -0.08
    èĪªæµ·
    -0.08
    alic
    -0.08
    æĤ
    -0.08
     retro
    -0.08
    POSITIVE LOGITS
    æĶ»åĩ»
    0.10
    æĮ¤
    0.09
    åĮºåŁŁæĢ§
    0.09
    éĺ²æĬ¤
    0.09
    éģıåĪ¶
    0.09
     Ashe
    0.08
    å¾Ĺä½ı
    0.08
    åįķ项
    0.08
     attack
    0.08
    ç´¯äºĨ
    0.08
    Activations Density 0.036%

    No Known Activations