© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9692
    Prev
    Next
    INDEX
    Explanations

    changes until

    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
    å¦Ĥä»Ĭ
    -0.10
    ä½ľåĩºäºĨ
    -0.10
    ç´§
    -0.10
    è¿Ļä¹Īå¤ļ
    -0.10
    /renderer
    -0.10
    åį³å°Ĩ
    -0.09
    åģļåĩºäºĨ
    -0.09
    çİ°ä»Ĭ
    -0.09
    æµģ转
    -0.09
    oyer
    -0.09
    POSITIVE LOGITS
     again
    0.12
    ä¸įä¼ļåĨį
    0.11
    åĨį度
    0.11
    again
    0.10
    éĤ£æŶ
    0.10
    åĨįä¹Łä¸į
    0.10
     novamente
    0.10
     Again
    0.09
     lagi
    0.09
    åıįè¿ĩæĿ¥
    0.09
    Activations Density 0.139%

    No Known Activations