© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37457
    Prev
    Next
    INDEX
    Explanations

    concept or topic introduction

    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¸įéĶĻ
    -0.10
    è¿Ľåħ¥åĪ°
    -0.09
    åł¡
    -0.09
    .defaults
    -0.08
    éĥ½å°Ĩ
    -0.08
    defaults
    -0.08
    ä¸įæĸŃæıIJé«ĺ
    -0.08
    noinspection
    -0.08
    ordination
    -0.08
     defaults
    -0.08
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.10
    çĽĬ
    0.10
     Aspect
    0.09
    éĥ¨åĪĨ
    0.09
    å·²ç»ıæĺ¯
    0.09
     alone
    0.09
     aspect
    0.09
    rying
    0.08
    ä¸Ģå¥Ĺ
    0.08
    ux
    0.08
    Activations Density 0.156%

    No Known Activations