© 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. 27653
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    寿
    -0.10
    å»ī
    -0.10
    çł´ç¢İ
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    Trail
    -0.09
    壽
    -0.08
    è´±
    -0.08
    ä»İæĿ¥
    -0.08
    ä»İæĿ¥æ²¡æľī
    -0.08
     Lid
    -0.08
    POSITIVE LOGITS
     somewhat
    0.12
    å·®çĤ¹
    0.12
    æľīäºĽäºº
    0.11
     sometimes
    0.11
    æľīæŶåĢĻ
    0.11
    æľīçĤ¹
    0.11
    åħ¬å¼Ģåıij
    0.11
    æľīäºĽ
    0.11
    æľīæŶ
    0.11
     пока
    0.11
    Activations Density 0.576%

    No Known Activations