© 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. 55227
    Prev
    Next
    INDEX
    Explanations

    data analysis and communication

    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
    éĢĢ
    -0.11
    ç»´ä¿®
    -0.09
    ä¾Ķ
    -0.09
    ç»´æĿĥ
    -0.09
    æĻĭ级
    -0.08
    [slot
    -0.08
    修建
    -0.08
    arts
    -0.08
    ç½ijç»ľä¼łæĴŃ
    -0.08
    å¼ķ
    -0.08
    POSITIVE LOGITS
    èĭįçĻ½
    0.11
    .datab
    0.11
    æ·ĺ
    0.10
    oves
    0.09
    çļĦæķ°æį®
    0.09
    ç»ĵæĻ¶
    0.09
    æķ°æį®åĪĨæŀIJ
    0.09
     Data
    0.09
     rawData
    0.09
    VOKE
    0.09
    Activations Density 0.173%

    No Known Activations