© 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. 50820
    Prev
    Next
    INDEX
    Explanations

    attack and 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
    åĭī强
    -0.12
    æĭ¯
    -0.10
    羦
    -0.10
    æ¯Ļ
    -0.09
    åĩºçĤī
    -0.09
    çī¹ä»·
    -0.09
    æįī
    -0.09
    æĬ¤èº«ç¬¦
    -0.09
    让åѦçĶŁ
    -0.09
    衲
    -0.09
    POSITIVE LOGITS
    æĶ»åĩ»
    0.23
     attack
    0.22
     attacks
    0.21
    æĶ»æĵĬ
    0.17
    attacks
    0.17
     Attacks
    0.17
     Attack
    0.17
    è¢Ńåĩ»
    0.17
    attack
    0.17
    _attack
    0.16
    Activations Density 0.080%

    No Known Activations