© 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. 50416
    Prev
    Next
    INDEX
    Explanations

    listing items that are included

    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
    ç¡®
    -0.10
    æ¶Ľ
    -0.10
    amas
    -0.09
    èµĦ
    -0.09
    .memory
    -0.09
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.09
    è®°å¿Ĩ
    -0.09
    sys
    -0.09
    Lord
    -0.09
    wend
    -0.09
    POSITIVE LOGITS
    åĪĨåĪ«æĺ¯
    0.12
    ä¸Ģæĺ¯
    0.11
    :
    0.10
    诸å¦Ĥ
    0.10
    ure
    0.10
    大家ä¸Ģèµ·
    0.09
    åĪĨåĪ«ä¸º
    0.09
    ï¼ļ
    0.09
    åĥıæĺ¯
    0.09
    ize
    0.09
    Activations Density 0.155%

    No Known Activations