© 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. 58936
    Prev
    Next
    INDEX
    Explanations

    time indicators

    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
    åł¡
    -0.10
    åºķæ°Ķ
    -0.09
    éļĽ
    -0.09
     cork
    -0.08
    åľ£è¯ŀèĬĤ
    -0.08
     Majesty
    -0.08
    ame
    -0.08
    æ¶Ķ
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    ipse
    -0.08
    POSITIVE LOGITS
    æ·±åĬłå·¥
    0.09
    MV
    0.09
    èµ·çĤ¹
    0.09
    åĶ®ç¥¨
    0.08
    éľ²
    0.08
    åIJį家
    0.08
    ä¹Łå¥½
    0.08
    å¯Į豪
    0.08
    Evt
    0.08
    .chapter
    0.08
    Activations Density 0.063%

    No Known Activations