© 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. 30017
    Prev
    Next
    INDEX
    Explanations

    bring positive or negative outcomes

    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
    åħ¬å¼Ģåıij
    -0.09
    åıĻ
    -0.09
    éĽĨè£ħ
    -0.09
    ç°¿
    -0.09
    åħijçİ°
    -0.09
    åħij
    -0.08
    emic
    -0.08
    ually
    -0.08
    enna
    -0.08
    çıł
    -0.08
    POSITIVE LOGITS
    带æĿ¥
    0.25
    带æĿ¥äºĨ
    0.23
    带æĿ¥çļĦ
    0.20
    帶ä¾Ĩ
    0.20
     brings
    0.18
     bring
    0.17
    带ç»Ļ
    0.17
     bringing
    0.16
    带åĪ°
    0.16
     brought
    0.15
    Activations Density 0.074%

    No Known Activations