© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    safety culture and compliance

    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
    çIJ¥
    -0.09
    è°µ
    -0.09
    管åĪ¶
    -0.08
    èĹķ
    -0.08
    åĩĨå¤ĩ
    -0.08
    anth
    -0.08
    service
    -0.08
    éºĿ
    -0.08
    oric
    -0.08
    ç¨Ĺ
    -0.08
    POSITIVE LOGITS
    ä¼ģä¸ļæĸĩåĮĸ
    0.12
    æĸĩåĮĸ建设
    0.11
    åħ¨åijĺ
    0.10
    空æ°Ķè´¨éĩı
    0.10
    æ°ĽåĽ´
    0.10
    èĬ¯
    0.10
     Lone
    0.09
    aines
    0.09
    é£İæ°Ķ
    0.09
    主ä½ĵ责任
    0.09
    Activations Density 0.090%

    No Known Activations