© 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. 26586
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĢ§å¼º
    -0.13
    -minded
    -0.13
    mente
    -0.12
    itel
    -0.10
    å®ĥçļĦ
    -0.10
    çļĦå°±æĺ¯
    -0.10
    rame
    -0.10
    -haired
    -0.09
    fully
    -0.09
    theless
    -0.09
    POSITIVE LOGITS
    /her
    0.27
    zelf
    0.16
    soever
    0.16
    -même
    0.15
    atically
    0.13
    èĢģ人家
    0.13
    ä¿©
    0.12
    /th
    0.12
    SELF
    0.10
    åĭĥåĭĥ
    0.10
    Activations Density 0.020%

    No Known Activations