© 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. 31214
    Prev
    Next
    INDEX
    Explanations

    oral bioavailability and absorption

    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
    åĨįä¹Ł
    -0.09
    æIJŃ
    -0.09
    è°ĥè¯ķ
    -0.08
    è¦Ĩ
    -0.08
    çĽĬ
    -0.08
     mad
    -0.08
    rese
    -0.08
    гоÑĢод
    -0.08
    ç©´
    -0.08
    ä»ĭ
    -0.08
    POSITIVE LOGITS
    åı£æľį
    0.12
    çľ¼çIJĥ
    0.09
    çīĩ
    0.09
    çĨĬ
    0.09
    kart
    0.09
    ç»Ļä»ĸ们
    0.09
    å¦ĤæĦı
    0.09
    иков
    0.09
    éľĪ
    0.09
    Repeated
    0.09
    Activations Density 0.341%

    No Known Activations