© 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. 32668
    Prev
    Next
    INDEX
    Explanations

    imagine something, wondering if

    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
    åĽĽä½į
    -0.10
    纯粹
    -0.10
    窨
    -0.10
    å²ĺ
    -0.09
    å¹²äºĭåĪĽä¸ļ
    -0.09
    楼å®ĩ
    -0.09
    åĩºè·¯
    -0.09
    广éĺĶçļĦ
    -0.08
    äºĶä¸Ģ
    -0.08
    CL
    -0.08
    POSITIVE LOGITS
    éķĸ
    0.09
     пÑĢоÑģ
    0.09
    abis
    0.09
    azole
    0.09
     lov
    0.09
    пÑĢоÑģ
    0.09
    ANGER
    0.08
    ảnh
    0.08
     disput
    0.08
    idar
    0.08
    Activations Density 0.251%

    No Known Activations