© 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. 52886
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æļĹ
    -0.09
     conf
    -0.09
    èµĦæĸĻæĺ¾ç¤º
    -0.08
     ripe
    -0.08
    æģļ
    -0.08
    çķĻ
    -0.08
    çIJĨ念
    -0.08
    çłĶ究表æĺİ
    -0.07
    æĮºå¥½
    -0.07
    èıł
    -0.07
    POSITIVE LOGITS
    说ä»Ģä¹Ī
    0.13
    åħ·ä½ĵçļĦ
    0.11
     оÑĤвеÑĤ
    0.11
    åıªèĥ½è¯´
    0.10
    åĽŀçŃĶ
    0.10
    çĪ¶åŃIJ
    0.10
    åĭī强
    0.10
    åĢľ
    0.10
     answer
    0.10
    éĻ¤æѤ
    0.09
    Activations Density 0.043%

    No Known Activations