© 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. 31461
    Prev
    Next
    INDEX
    Explanations

    time passed or current state

    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
    æıĨ
    -0.10
    ivity
    -0.09
    忽
    -0.09
    罩
    -0.09
     Beg
    -0.08
     materially
    -0.08
    åĢª
    -0.08
    å¨ģèĥģ
    -0.08
    主ä¹īæĢĿæĥ³
    -0.08
    Trap
    -0.08
    POSITIVE LOGITS
    ä»ĸå·²ç»ı
    0.11
    å·²ç»ıæĪIJ为
    0.10
    æ·ĺæ±°
    0.10
    ught
    0.10
     already
    0.10
    æĹ©å·²
    0.10
    çĨŁçŁ¥
    0.10
    å·²ç»ı
    0.09
    å·²ç¶ĵ
    0.09
    å·²ç»ı被
    0.09
    Activations Density 0.035%

    No Known Activations