© 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. 49142
    Prev
    Next
    INDEX
    Explanations

    offensive behavior or objections

    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
    亡
    -0.10
    zer
    -0.09
    åIJ¹
    -0.09
    ierre
    -0.09
    alem
    -0.09
     Wet
    -0.09
    еÑĩен
    -0.08
    æ¶Ī
    -0.08
     chase
    -0.08
    æĻĴ
    -0.08
    POSITIVE LOGITS
    åİĮæģ¶
    0.22
    讨åİĮ
    0.22
    æģ¶å¿ĥ
    0.17
    åıįæĦŁ
    0.17
    çĥ¦
    0.15
    æĨİ
    0.14
    éĦĻ
    0.14
    åİĮ
    0.14
    åİŃ
    0.13
    å«Įå¼ĥ
    0.13
    Activations Density 0.064%

    No Known Activations