© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4678
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    æĤ²åĵĢ
    -0.10
    å·¥åķĨ
    -0.10
    utor
    -0.10
    æ±īåł¡
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
    ninger
    -0.09
    è¡®
    -0.09
    秦çļĩ
    -0.09
    女è£ħ
    -0.08
    çĶŁæľº
    -0.08
    POSITIVE LOGITS
    eve
    0.09
    èµĸ
    0.08
    rou
    0.08
    çļĦä¸Ģåijĺ
    0.08
    æķ²
    0.08
    /files
    0.08
    åģĥ
    0.08
    .station
    0.08
    æµģä¼ł
    0.08
    ãģ¸
    0.08
    Activations Density 0.173%

    No Known Activations