© 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. 61308
    Prev
    Next
    INDEX
    Explanations

    make decisions or promotions

    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
    .tap
    -0.10
    orny
    -0.09
    ç´łé£Ł
    -0.09
    å®ŀéĻħæĥħåĨµ
    -0.09
    SSI
    -0.09
    æ°ijæĹıæĸĩåĮĸ
    -0.08
    ä¸ľè¥¿
    -0.08
    èıĬèĬ±
    -0.08
    ç³»åĪĹ产åĵģ
    -0.08
    çļĦä¸ľè¥¿
    -0.08
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.09
    çļĦå°±æĺ¯
    0.08
    ä»Ģä¹Īæł·çļĦ
    0.08
    å½ĵçĦ¶æĺ¯
    0.08
    å¹²èĦĨ
    0.08
    assis
    0.08
    ä¹Łæĺ¯ä¸Ģç§į
    0.08
    è¿Ļæł·çļĦ
    0.08
    ĪæĿĥ
    0.08
    attr
    0.08
    Activations Density 1.970%

    No Known Activations