© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    speaking even

    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
    éĥ¨ä»½
    -0.10
    é©Ń
    -0.08
    èĢģå¦Ī
    -0.08
    çĶľçĶľ
    -0.08
    èĩªèIJ¥
    -0.08
    owy
    -0.08
    æĦıåij³
    -0.08
    æ¯ı次
    -0.08
    è¾ĥ大
    -0.08
    åħħåĪĨåıijæĮ¥
    -0.08
    POSITIVE LOGITS
    bih
    0.10
     OK
    0.09
    ç»Ļä½łä»¬
    0.09
    presso
    0.09
    è·ijäºĨ
    0.09
    ãģªãģĦãĤĪãģĨãģ«
    0.09
    å¾Īæ¸ħæ¥ļ
    0.09
    èĪī
    0.08
    è°Ī
    0.08
    就好
    0.08
    Activations Density 0.107%

    No Known Activations