© 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. 22896
    Prev
    Next
    INDEX
    Explanations

    data analysis and trends

    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
    æĪIJåĬŁçļĦ
    -0.11
    è§Ĥæij©
    -0.10
    æIJľ
    -0.09
    èĥ½åĬĽå¼º
    -0.08
     sketches
    -0.08
    示èĮĥ
    -0.08
    åľ¨èģĮ
    -0.08
     оÑĤказ
    -0.08
    å®ŀè·µ
    -0.08
    æĪIJåĬŁ
    -0.08
    POSITIVE LOGITS
    çļĦæķ°æį®
    0.14
    æķ°æį®
    0.12
     data
    0.12
    ç»Łè®¡æķ°æį®
    0.11
    ãĥĩãĥ¼ãĤ¿
    0.11
    data
    0.10
     æķ°æį®
    0.10
     Data
    0.10
    åı£å¾Ħ
    0.10
    æķ¸æĵļ
    0.10
    Activations Density 0.230%

    No Known Activations