© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52950
    Prev
    Next
    INDEX
    Explanations

    safe, effective, flexible, efficient

    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
    llum
    -0.09
    èĸ°
    -0.09
    æįħ
    -0.09
    åĪ¶åº¦æĶ¹éĿ©
    -0.08
    ä»Ģä¹Īäºĭ
    -0.08
    è¿Ļç§įæĥħåĨµ
    -0.08
    æ¹®
    -0.08
    é²²
    -0.08
    éĥ¨ä»½
    -0.08
    allo
    -0.08
    POSITIVE LOGITS
    满æĦıçļĦ
    0.13
    é«ĺæķĪçļĦ
    0.12
    å°½åı¯èĥ½
    0.11
    å¼Ģ端
    0.10
    åıĪ
    0.10
    åı¯éĿłçļĦ
    0.09
    æľīæķĪçļĦ
    0.09
    åıĪ好
    0.09
    ä¸Ķ
    0.09
     yet
    0.09
    Activations Density 0.179%

    No Known Activations