© 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. 7124
    Prev
    Next
    INDEX
    Explanations

    west

    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
    èĭĮ
    -0.10
    åħ¨çIJĥç»ıæµİ
    -0.09
    羡
    -0.09
    缴å±ŀ
    -0.08
     oci
    -0.08
    erate
    -0.08
    OCI
    -0.08
     reap
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    inst
    -0.08
    POSITIVE LOGITS
    iful
    0.10
    å¥ĭæĸĹ缮æłĩ
    0.10
     haircut
    0.10
    éĥ½å¸ĤæĬ¥
    0.09
    æģ¯
    0.09
    logan
    0.09
    æĻº
    0.09
    çĥŁçģ«
    0.09
    rut
    0.08
    erson
    0.08
    Activations Density 0.031%

    No Known Activations