© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51454
    Prev
    Next
    INDEX
    Explanations

    what can, when is, who wouldn

    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
    æŁIJç§į
    -0.09
    ä»ŀ
    -0.08
    tram
    -0.08
    èµ·äºĨ
    -0.08
    uner
    -0.08
    寮
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
    åİĺ
    -0.08
    åıĺçİ°
    -0.08
    ä¸įæĩĪ
    -0.08
    POSITIVE LOGITS
    æĢİä¹Īåı¯èĥ½
    0.13
    éļ¾éģĵ
    0.12
    è¿ĺæľīä»Ģä¹Ī
    0.11
    æĢİèĥ½
    0.11
    å²Ĥ
    0.11
    æĢİä¹Īä¼ļ
    0.11
    æľīä»Ģä¹Ī
    0.10
    ä½ķå¿ħ
    0.10
    åĩŃä»Ģä¹Ī
    0.09
     Beste
    0.09
    Activations Density 0.029%

    No Known Activations