© 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. 53115
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and degrees

    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
    abox
    -0.09
    碣
    -0.09
    å¥Ķ
    -0.09
    æĪĭ
    -0.09
    桶
    -0.09
    ÑĦи
    -0.09
    olib
    -0.09
    engo
    -0.08
    岸边
    -0.08
    agues
    -0.08
    POSITIVE LOGITS
    éĥ¨
    0.12
    ç³»
    0.12
     department
    0.10
    éĥ¨éĥ¨éķ¿
    0.10
    éĥ¨ä¸»ä»»
    0.09
    çļĦæĥħ
    0.09
    ä¸ĵä¸ļçļĦ
    0.09
    ç±»
    0.09
    械
    0.09
    ä¹ĭ家
    0.08
    Activations Density 0.175%

    No Known Activations