© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36831
    Prev
    Next
    INDEX
    Explanations

    unit test, unit mix, unit serial

    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°¼äºļ
    -0.09
    yer
    -0.09
    åŀł
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    对æĪij说
    -0.09
    ãĤ¶
    -0.09
    æĻĹ
    -0.09
    atology
    -0.09
    èĢħçļĦ
    -0.09
    oter
    -0.09
    POSITIVE LOGITS
    errupted
    0.16
    IALIZED
    0.14
    itarian
    0.14
    itial
    0.12
    arity
    0.11
    errupt
    0.11
    æĹ¶éĹ´åĨħ
    0.11
    ARY
    0.11
    ized
    0.10
    ary
    0.10
    Activations Density 0.081%

    No Known Activations