© 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. 32052
    Prev
    Next
    INDEX
    Explanations

    won awards and achievements

    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
    åŃ°
    -0.10
    <Func
    -0.10
     давно
    -0.10
    .ba
    -0.10
    椰
    -0.09
    ба
    -0.09
    .Startup
    -0.09
     Bailey
    -0.09
    AspNet
    -0.09
    /Branch
    -0.09
    POSITIVE LOGITS
     itself
    0.10
    åľ¨åĽ½å¤ĸ
    0.09
    é«ĺä½į
    0.09
    åIJĦåľ°
    0.09
    ä½Ĩå®ĥ
    0.09
    å¤ļåľ°
    0.08
    æݨåIJij
    0.08
    åĽłä¸ºå®ĥ
    0.08
    æĺ¯ä¸Ģéĥ¨
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    Activations Density 0.163%

    No Known Activations