© 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. 37150
    Prev
    Next
    INDEX
    Explanations

    discoloration, rust, dirt, shine, patina, weathered

    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
     borderTop
    -0.11
    汨
    -0.10
    èĢĹ
    -0.09
    æĨ¬
    -0.09
    åıĶåıĶ
    -0.09
    VRT
    -0.09
    URT
    -0.08
    对äºİæĪij们
    -0.08
     unchecked
    -0.08
    ç»ĦæĪIJçļĦ
    -0.08
    POSITIVE LOGITS
    èĥİ
    0.10
    ebin
    0.09
    åİĨåı²æĸ°
    0.08
    é«ĺåİŁ
    0.08
    ulle
    0.08
    ä¸įä¹ħ
    0.08
    åīįè¡Į
    0.08
    æīĵæŃ»
    0.08
    æ¯ķ
    0.08
    驳
    0.08
    Activations Density 0.042%

    No Known Activations