© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20676
    Prev
    Next
    INDEX
    Explanations

    cloak and dagger

    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
    æµģä¼ł
    -0.09
    积æ·Ģ
    -0.09
    åŁºçŁ³
    -0.09
    æī¿æİ¥
    -0.08
    alone
    -0.08
    çĬĢ
    -0.08
    æĮĤçīĮ
    -0.08
    å®ļçĤ¹
    -0.08
    æĬĵ
    -0.08
    urple
    -0.08
    POSITIVE LOGITS
    åĽ°éļ¾
    0.10
    åıijåħī
    0.10
    åĽ°éĽ£
    0.09
    åĿı
    0.09
    åŁºæľ¬ä¸Ĭ
    0.09
    客æłĪ
    0.09
    æķij人
    0.09
    åį±
    0.09
    æķijæĬ¤
    0.09
    ä¸Ģé¡¿
    0.09
    Activations Density 0.083%

    No Known Activations