© 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. 32264
    Prev
    Next
    INDEX
    Explanations

    blood circulation and flow

    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
    ä¸Ģéģĵ
    -0.10
    çŁ¥
    -0.10
    åĮĹæĸ¹
    -0.09
     Advent
    -0.09
     пÑĢоб
    -0.09
    æģIJ
    -0.09
    çĪª
    -0.09
    aire
    -0.09
    çĨ¨
    -0.09
    ç¢İ
    -0.08
    POSITIVE LOGITS
    è¡Ģ液
    0.18
    æµģæ·Į
    0.15
     кÑĢови
    0.13
     bloodstream
    0.11
     blood
    0.11
    è¡Ģ液循çݯ
    0.11
    è¡Ģ
    0.11
     máu
    0.10
     circulation
    0.10
    æµĥ
    0.10
    Activations Density 0.069%

    No Known Activations