© 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. 6651
    Prev
    Next
    INDEX
    Explanations

    enlightenment communities

    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
    大夫
    -0.09
    å¼Ĥ
    -0.09
    æĤ£
    -0.09
    代
    -0.08
    éī´
    -0.08
    unks
    -0.08
    å°¼äºļ
    -0.08
    жен
    -0.08
    webs
    -0.08
    æĿ¡è§Ħå®ļ
    -0.08
    POSITIVE LOGITS
    æį¶
    0.09
    æĬ¤èº«
    0.09
    åºķå±Ĥ
    0.09
    修身
    0.09
    èĬ±çĶŁ
    0.09
    èIJ±
    0.09
    åºķçĽĺ
    0.09
    åľ¨çº¿åĴ¨è¯¢
    0.08
    åĬ©çIJĨ
    0.08
    é«ĺä»·
    0.08
    Activations Density 0.048%

    No Known Activations