© 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. 53489
    Prev
    Next
    INDEX
    Explanations

    URLs and technical terms

    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
    çķ´
    -0.10
    bing
    -0.09
    TB
    -0.09
    èĩªæĦ¿
    -0.08
    åįļ主
    -0.08
    çĤĬ
    -0.08
     torso
    -0.08
    su
    -0.08
    æĭĸ
    -0.08
    cam
    -0.08
    POSITIVE LOGITS
    æĭĽèĤ¡
    0.10
    ä¸Ńä»ĭæľºæŀĦ
    0.10
    æıĸ
    0.10
     Powers
    0.10
    å¼ķæĿ¥
    0.09
    è¿ľç¦»
    0.09
    亮丽
    0.09
    ä¸Ģåij³
    0.09
    ãģ£ãģ±
    0.09
     günlük
    0.09
    Activations Density 0.003%

    No Known Activations