© 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. 39433
    Prev
    Next
    INDEX
    Explanations

    volunteer Services

    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
    å¿ĹæĦ¿
    -0.09
    -0.09
    oko
    -0.09
    ây
    -0.08
    责任人
    -0.08
    ÑĮÑı
    -0.08
    imizer
    -0.08
    ffer
    -0.08
    æ¶Įçİ°åĩº
    -0.08
    èݳ
    -0.08
    POSITIVE LOGITS
    ниÑĨа
    0.12
     един
    0.09
    iaux
    0.09
     sieve
    0.08
    ëį°
    0.08
     Jade
    0.08
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.08
    ary
    0.08
    ously
    0.08
    ships
    0.08
    Activations Density 0.004%

    No Known Activations