© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 23623
    Prev
    Next
    INDEX
    Explanations

    legal roles or titles

    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
    åı¸é©¬
    -0.11
    æĬ¤å£«
    -0.11
    è¶Ĭ
    -0.10
    大夫
    -0.09
    å°±è¶Ĭ
    -0.09
    å¾ĭå¸ĪäºĭåĬ¡
    -0.09
    é£İåIJ¹
    -0.09
    è¯ķ管
    -0.09
    ç½ijç«Ļé¦ĸ页
    -0.09
    åı¸
    -0.08
    POSITIVE LOGITS
    éĢł
    0.10
    -girl
    0.10
    认
    0.09
    è®¤çľŁ
    0.09
    æľīäºĽ
    0.09
    asure
    0.09
    æĦıåij³
    0.09
    ä¸ĵé¢ĺ
    0.09
    itur
    0.08
    çĤ¹è¯Ħ
    0.08
    Activations Density 0.052%

    No Known Activations