© 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. 33748
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    æĪij们éĥ½
    -0.09
    unt
    -0.09
    æĪijä¸Ģ缴
    -0.09
    çļĦ人éĥ½
    -0.08
    æĪIJ为ä¸Ģ个
    -0.08
    ift
    -0.08
    quire
    -0.08
    åIJģ
    -0.08
    综åIJĪæĢ§
    -0.08
     people
    -0.08
    POSITIVE LOGITS
    们çļĦ
    0.13
    们
    0.12
    åĢij
    0.11
     whose
    0.10
    å®ŀéĻħæݧåĪ¶
    0.10
    ä¸ĢæŦ
    0.09
    è¦ģçľĭ
    0.09
    äºĮ线
    0.09
    ä¼ļè§īå¾Ĺ
    0.09
    ially
    0.09
    Activations Density 0.173%

    No Known Activations