© 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. 58118
    Prev
    Next
    INDEX
    Explanations

    government websites or official sites

    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
    ç¼ĸåĨĻ
    -0.12
    ç¼ĸè¾ij
    -0.10
    è¿ĺåİŁ
    -0.10
    ç·¨
    -0.09
    å®Ī
    -0.09
    ä¸ĢéŨ
    -0.08
    è¿Ħ
    -0.08
    éī´å®ļ
    -0.08
    endum
    -0.08
    审æī¹
    -0.08
    POSITIVE LOGITS
    å®ĺæĸ¹ç½ijç«Ļ
    0.15
    å®ĺç½ij
    0.12
     поÑĢÑĤал
    0.11
     website
    0.11
    ç½ijä¸Ĭ
    0.10
    ç½ijç«Ļ
    0.10
    ä¿¡æģ¯åħ¬å¼Ģ
    0.10
    缸åħ³ä¿¡æģ¯
    0.10
     official
    0.10
    éŨæĪ·ç½ijç«Ļ
    0.10
    Activations Density 0.072%

    No Known Activations