© 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. 63466
    Prev
    Next
    INDEX
    Explanations

    thanks to

    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
    ä»Ģä¹Īåı«
    -0.10
    渴
    -0.10
    èĽĨ
    -0.09
    以æѤ
    -0.09
    çļĦç²¾ç¥ŀ
    -0.09
    å¾Ĵ
    -0.09
    æħİ
    -0.09
    ree
    -0.09
     krist
    -0.09
    åħ¨è¿ĩç¨ĭ
    -0.09
    POSITIVE LOGITS
    å¾ĹçĽĬäºİ
    0.11
    fully
    0.09
    ously
    0.09
     grâce
    0.09
    ably
    0.08
    oco
    0.08
    EMENT
    0.08
    ä¸Ģçķª
    0.08
    eff
    0.08
    æ²®
    0.08
    Activations Density 0.041%

    No Known Activations