© 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. 27237
    Prev
    Next
    INDEX
    Explanations

    scoring points or yards

    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
    åħ¥åı£
    -0.10
    ICODE
    -0.09
     вообÑīе
    -0.08
     вÑĭпÑĥÑģ
    -0.08
    çıįæĥľ
    -0.08
    à¸Ńà¸ļ
    -0.08
    æĶ¶è´¹æłĩåĩĨ
    -0.08
     маÑĢ
    -0.08
    åĢļ
    -0.08
    CODE
    -0.08
    POSITIVE LOGITS
    çĺ¦
    0.09
    好å¤Ħ
    0.09
    æīĢéľĢ
    0.09
    hani
    0.09
    åIJĮæĦı
    0.09
    å¾Īå¼Ģå¿ĥ
    0.08
    大å¥ĸ
    0.08
    WARDS
    0.08
     hòa
    0.08
    apes
    0.08
    Activations Density 0.144%

    No Known Activations