© 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. 50005
    Prev
    Next
    INDEX
    Explanations

    roles and positions

    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
    æªĢ
    -0.08
    è¿Ļåıª
    -0.08
    èĦijåŃIJéĩĮ
    -0.08
    åŃIJéĩĮ
    -0.08
    ä¸įå®ļ
    -0.08
    æģ°å¥½
    -0.08
    åĪļ好
    -0.08
    .classes
    -0.08
     öz
    -0.07
    èĥ½å¤Ł
    -0.07
    POSITIVE LOGITS
    çļĦ身份
    0.15
    身份
    0.14
     status
    0.12
    称åı·
    0.12
    hood
    0.12
    ä¹ĭåĬ¿
    0.11
    èµĦæł¼
    0.11
    çļĦè§Ĵèī²
    0.11
    çļĦåľ°ä½į
    0.10
    ë¡ľìĦľ
    0.10
    Activations Density 0.404%

    No Known Activations