© 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. 2387
    Prev
    Next
    INDEX
    Explanations

    internal network communication

    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
    åĪĨ管
    -0.09
    çļĦçľ¼
    -0.09
    æ²¼
    -0.09
    Drawable
    -0.08
    acre
    -0.08
    ç¿Ĵ
    -0.08
    าย
    -0.08
    avage
    -0.08
    azzi
    -0.08
    IVO
    -0.08
    POSITIVE LOGITS
    ä¸ĬçıŃ
    0.08
    PHY
    0.08
    åŁºç¡Ģ设æĸ½
    0.08
    åįľ
    0.08
    éĿĸ
    0.08
    èµĮ
    0.08
    åįķ身
    0.08
    å§Ĭ妹
    0.08
    ÑĨии
    0.08
     вÑĭп
    0.08
    Activations Density 0.010%

    No Known Activations