© 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. 58620
    Prev
    Next
    INDEX
    Explanations

    Victorian slums or historical cities

    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
    è®·
    -0.12
    æķıæĦŁ
    -0.11
    åľŃ
    -0.10
    æIJ¬å®¶
    -0.10
    omm
    -0.10
    æ»ijéĽª
    -0.10
     год
    -0.10
    æ°¸ä¹ħ
    -0.10
    éĢĬ
    -0.10
    忸
    -0.09
    POSITIVE LOGITS
     Soup
    0.10
    è¡Ĺéģĵ
    0.10
    伦æķ¦
    0.09
     Dickens
    0.09
     London
    0.09
    æ¢Ĩ
    0.08
    çłģ头
    0.08
    大è¡Ĺ
    0.08
    æĻļæĬ¥
    0.08
    dyn
    0.08
    Activations Density 0.148%

    No Known Activations