© 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. 52687
    Prev
    Next
    INDEX
    Explanations

    extra effort or steps

    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±¥èģĮ
    -0.10
    æ½¼
    -0.09
    æľĢ好çļĦ
    -0.09
    eltas
    -0.08
    atar
    -0.08
    æµij
    -0.08
    .targets
    -0.08
    ä»ĸ对
    -0.08
    _STRUCTURE
    -0.08
    寸
    -0.08
    POSITIVE LOGITS
     effort
    0.14
    åĪ»æĦı
    0.13
    åįĥæĸ¹çĻ¾è®¡
    0.13
    çī¹æĦı
    0.12
     pains
    0.12
     efforts
    0.11
     ÑĥÑģили
    0.11
    åĬªåĬĽ
    0.11
    è²»
    0.10
    è´¹
    0.10
    Activations Density 0.062%

    No Known Activations