© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21369
    Prev
    Next
    INDEX
    Explanations

    fluid collection and transport

    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
    hill
    -0.10
    isci
    -0.09
     Dust
    -0.09
     dust
    -0.09
    ä½¥
    -0.08
    æĥ³æ³ķ
    -0.08
    åĨħåľ°
    -0.08
    æłİ
    -0.08
    æĭīæĸ¯
    -0.08
    çľ¼åħī
    -0.08
    POSITIVE LOGITS
    athom
    0.09
    bourne
    0.09
    ä¸Ģç¢Ĺ
    0.09
     Swords
    0.09
    WithOptions
    0.08
    raries
    0.08
    天èĬ±
    0.08
    êu
    0.08
    æĭħ忧
    0.08
    oti
    0.08
    Activations Density 0.057%

    No Known Activations