© 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. 30133
    Prev
    Next
    INDEX
    Explanations

    Bosch or Bosnia

    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
    uffed
    -0.10
    angan
    -0.09
    ãģ¨ãĤĬ
    -0.08
    ãģ®ãģĮ
    -0.08
    kur
    -0.08
    edList
    -0.08
    Looper
    -0.08
    éĩľ
    -0.08
    eds
    -0.08
    esar
    -0.08
    POSITIVE LOGITS
    å¨ĺ
    0.10
    ties
    0.10
    è¦ģçŁ¥éģĵ
    0.10
    RED
    0.10
    åİŁä¾Ĩ
    0.09
    .swagger
    0.09
    æĿĵ
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    éĹ®éĹ®
    0.09
    cloth
    0.09
    Activations Density 0.011%

    No Known Activations