© 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. 38740
    Prev
    Next
    INDEX
    Explanations

    advance notice

    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
    åijĬ
    -0.09
    强æľīåĬĽ
    -0.09
    arf
    -0.08
    æĦŁæŁĵèĢħ
    -0.08
     fm
    -0.08
    车ç«Ļ
    -0.08
    istrator
    -0.08
    åĭ¾
    -0.08
    ç½ij页
    -0.08
    çķĻ
    -0.08
    POSITIVE LOGITS
    è¶Ĭ好
    0.10
    åµĬ
    0.09
    åįĬæľĪ
    0.08
    åıijå±ķ缮æłĩ
    0.08
    tape
    0.08
    寡
    0.08
    æģ¨ä¸įå¾Ĺ
    0.08
    鹤
    0.08
    éĻªåIJĮ
    0.08
    æ²Ļé¾Ļ
    0.08
    Activations Density 0.008%

    No Known Activations