© 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. 5240
    Prev
    Next
    INDEX
    Explanations

    being part of

    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
    ways
    -0.10
    åħ¥èĤ¡
    -0.09
    angan
    -0.09
    çł´äº§
    -0.09
    ден
    -0.08
    zon
    -0.08
    áĥ§
    -0.08
    è¹²
    -0.08
    udas
    -0.08
    éŃĶé¾Ļ
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īéĥ½
    0.09
    æľīè¿Ļæł·çļĦ
    0.09
    åıijçĶŁäºĨ
    0.09
    è¿¢
    0.09
    hest
    0.08
     пÑĢоиÑģ
    0.08
    åİļåİļ
    0.08
    ä¹ĭ家
    0.08
     BaseType
    0.08
    åºŀ大
    0.08
    Activations Density 0.029%

    No Known Activations