© 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. 4112
    Prev
    Next
    INDEX
    Explanations

    `in` your, `in` mail, `in` English

    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
    æĬ¢
    -0.09
    å«ĸ
    -0.09
    4
    -0.08
    éļĪ
    -0.08
    åĢŃ
    -0.08
    æIJ¶
    -0.08
    伺
    -0.08
     hare
    -0.08
    urg
    -0.08
    åĭ¤
    -0.08
    POSITIVE LOGITS
    ayout
    0.10
    å°±å¦ĤåIJĮ
    0.09
     nud
    0.09
    寧
    0.09
    ADVERTISEMENT
    0.09
    ç°¸
    0.09
     tut
    0.09
     bul
    0.09
    注æĺİåĩºå¤Ħ
    0.09
    æķ´é¡¿
    0.08
    Activations Density 0.041%

    No Known Activations