© 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. 55821
    Prev
    Next
    INDEX
    Explanations

    . We

    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
    برÙĬ
    -0.08
    åĢĶ
    -0.08
    ambi
    -0.08
    æĬķåħ¥
    -0.08
     kc
    -0.08
    âm
    -0.08
    å·®çĤ¹
    -0.08
    /github
    -0.08
     اÙĦØ£ÙĪ
    -0.07
    åĴ
    -0.07
    POSITIVE LOGITS
    ä¸į代表
    0.12
    ãģĶåĪ©çĶ¨
    0.10
    缮çĿ¹
    0.10
    æīĵçĿĢ
    0.09
     Nack
    0.09
    ä»ħä¾Ľ
    0.09
    æľ¬ç½ij
    0.09
    å°ijä¸įäºĨ
    0.09
    天èĬ±
    0.09
    èķī
    0.09
    Activations Density 0.078%

    No Known Activations