© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    signs and omens

    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
    unger
    -0.09
     пÑĢÑı
    -0.09
    åĮħ袱
    -0.09
    èĵĦ
    -0.09
    ç²¾ç»Ĩ
    -0.09
    å¿ĥæĥħ
    -0.09
    agger
    -0.09
    æľīèī²éĩijå±ŀ
    -0.09
    é«ĺä½İ
    -0.09
    åIJĦè¡Į
    -0.09
    POSITIVE LOGITS
    å·§åIJĪ
    0.12
     coincidence
    0.09
    éģĺ
    0.09
    omens
    0.09
    åģľçķĻåľ¨
    0.08
    çĶ²
    0.08
    é¢ijç¹ģ
    0.08
     Jah
    0.08
    çĿ½
    0.08
    idan
    0.08
    Activations Density 0.056%

    No Known Activations