© 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. 62937
    Prev
    Next
    INDEX
    Explanations

    graduated with an academic degree

    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
    ä¸Ĭå²Ĺ
    -0.10
    å¾Ģä¸ĭ
    -0.10
    ä¹ĭæĪĺ
    -0.09
    笼
    -0.09
    æĿ¥åİĨ
    -0.08
    æīĵä»Ĺ
    -0.08
    ä¸įä¸Ĭ
    -0.08
    åķ»
    -0.08
    æľ¬ç«Ļ
    -0.08
     Tone
    -0.08
    POSITIVE LOGITS
    ä¸ĩçī©
    0.09
    è¾ħ导åijĺ
    0.08
    ä¼ĺå¼Ĥ
    0.08
    åī¯
    0.08
    rita
    0.08
     emphasis
    0.08
    è¿ĺéľĢè¦ģ
    0.08
    ä¼´æľī
    0.08
    emachine
    0.08
    Ó¯
    0.08
    Activations Density 0.039%

    No Known Activations