© 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. 6476
    Prev
    Next
    INDEX
    Explanations

    multiple, several, knee high, practice

    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¢Į
    -0.09
    饮åĵģ
    -0.09
    次è¦ģ
    -0.08
    çİ©åħ·
    -0.08
    饮çĶ¨æ°´
    -0.08
    æ¿Ĵ
    -0.08
    ContentAlignment
    -0.08
    饮æĸĻ
    -0.08
    æģIJæĢĸ
    -0.08
    çİ»çĴĥ
    -0.08
    POSITIVE LOGITS
    æľĪç»ı
    0.11
    窿
    0.09
    èıģ
    0.09
    è£Ĩ
    0.08
    ä¹°çļĦ
    0.08
    æħķ
    0.08
     discreet
    0.08
    裥
    0.08
     mens
    0.08
    volution
    0.08
    Activations Density 0.038%

    No Known Activations