© 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. 55652
    Prev
    Next
    INDEX
    Explanations

    researchers and outcomes

    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
    覽
    -0.10
    åįĬå²Ľ
    -0.10
    åħ¬æĬ¥
    -0.09
    ÙĦÙĥ
    -0.09
    éļıä¹ĭ
    -0.09
    éĻĦå±ŀ
    -0.09
    sink
    -0.09
    _DM
    -0.08
    ом
    -0.08
    ldb
    -0.08
    POSITIVE LOGITS
    为ä¾ĭ
    0.14
    æĪĸåħ¶ä»ĸ
    0.14
    æĪĸèĢħåħ¶ä»ĸ
    0.14
    çī¹åĪ«æĺ¯
    0.13
    å°¤åħ¶
    0.12
    ä¹Łä¸įä¾ĭå¤ĸ
    0.12
    以åıĬåħ¶ä»ĸ
    0.12
    åıĬåħ¶ä»ĸ
    0.12
    å°¤åħ¶æĺ¯
    0.12
    尤为
    0.12
    Activations Density 0.861%

    No Known Activations