© 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. 31080
    Prev
    Next
    INDEX
    Explanations

    environmental topics and issues

    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
    伤åı£
    -0.09
    æĪŁ
    -0.08
    çīµå¼ķ
    -0.08
    Vent
    -0.08
     loosen
    -0.08
    æµģéĢļ
    -0.08
    æ°ijæĶ¿
    -0.08
     Attr
    -0.08
     circulation
    -0.07
    éĽªèĬ±
    -0.07
    POSITIVE LOGITS
    çݯä¿Ŀ
    0.20
    çݯå¢ĥä¿ĿæĬ¤
    0.17
    åľ°çIJĥ
    0.17
     environmental
    0.16
     Environmental
    0.15
    Environmental
    0.14
    çĶŁæĢģæĸĩæĺİ
    0.14
    .Environment
    0.13
    ä½İ碳
    0.13
    绿èī²åıijå±ķ
    0.13
    Activations Density 0.148%

    No Known Activations