© 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. 33837
    Prev
    Next
    INDEX
    Explanations

    gastrointestinal tract permeability

    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
    å¾Ĥ
    -0.11
    ports
    -0.10
    庵
    -0.10
    åĽĽæĸ¹
    -0.10
    ä½ľé£İ
    -0.09
    åİ»è¿ĩ
    -0.09
    iske
    -0.09
    è¶Ĭæĺ¯
    -0.09
    Descriptor
    -0.09
    è°ĥåīĤ
    -0.09
    POSITIVE LOGITS
    èłķ
    0.09
    èĤł
    0.09
    éĩĬ
    0.09
     bowed
    0.08
     bức
    0.08
    à¹Ģà¸ģร
    0.08
    è¿Ľåħ¥
    0.08
    ban
    0.08
    æ¯ģ
    0.08
    å£ģ
    0.08
    Activations Density 0.253%

    No Known Activations