© 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. 27602
    Prev
    Next
    INDEX
    Explanations

    Royal Academy, drawing from life

    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
    ENA
    -0.10
    æī¬
    -0.10
    .Pod
    -0.09
     Hasan
    -0.09
    è¿IJè¡Į
    -0.09
    æīįè¡Į
    -0.09
    PERT
    -0.09
    æħ·
    -0.09
    åľ°å¸¦
    -0.09
    æѤç§į
    -0.09
    POSITIVE LOGITS
    模çī¹
    0.11
    ç»ı纪人
    0.09
    ç»ĺçĶ»
    0.09
    æķĻåŃ¦è´¨éĩı
    0.09
     наÑĤÑĥÑĢ
    0.08
    åŁİ乡
    0.08
    å´ĩ
    0.08
    è¯Ĭ
    0.08
    å¤ļä½į
    0.08
    .typ
    0.08
    Activations Density 0.114%

    No Known Activations