© 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. 4708
    Prev
    Next
    INDEX
    Explanations

    circulation and blood 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
    è¾Ľ
    -0.09
    é¾Ļ头
    -0.09
    æ¤ħ
    -0.08
    باÙĥ
    -0.08
    _pipe
    -0.08
    éĩijæ²Ļ
    -0.08
    管
    -0.08
    ìĥĮ
    -0.08
    å£ķ
    -0.08
    ddy
    -0.08
    POSITIVE LOGITS
    æµģéĢļ
    0.17
     circulation
    0.15
    è¡Ģ液循çݯ
    0.13
    æµģåĬ¨
    0.13
    circ
    0.11
     commerce
    0.11
     Circ
    0.11
     traffic
    0.10
    循çݯ
    0.10
     circ
    0.10
    Activations Density 0.102%

    No Known Activations