© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51341
    Prev
    Next
    INDEX
    Explanations

    strep, pyogenes, disc, culture

    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
    enders
    -0.09
    èĽĩ
    -0.09
     Bud
    -0.09
    tera
    -0.08
    æĸ°åĮº
    -0.08
    á»į
    -0.08
    еле
    -0.08
    è¿Ļéĥ¨åĪĨ
    -0.08
     Bacon
    -0.08
    bud
    -0.08
    POSITIVE LOGITS
     Gram
    0.11
    uria
    0.10
    Gram
    0.09
    -runner
    0.09
    à¹ģà¸ļ
    0.09
    OrNull
    0.09
    è¢ħ
    0.08
    ungi
    0.08
    åī¯
    0.08
    ä¸įèµ·
    0.08
    Activations Density 0.315%

    No Known Activations