© 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. 54484
    Prev
    Next
    INDEX
    Explanations

    time and sequence

    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
    ä¸įåIJ«
    -0.11
    åĪĿ次
    -0.10
    _sr
    -0.10
    èĩ³äºİ
    -0.09
    versed
    -0.09
    ugen
    -0.08
    ä¸įåıĺ
    -0.08
    ä½ķ度
    -0.08
    .Unity
    -0.08
    oki
    -0.08
    POSITIVE LOGITS
    æŃ£åĢ¼
    0.13
    åĪļ好
    0.12
     coinc
    0.11
    æĴŀ
    0.10
    æģ°
    0.10
    ä»ĵ
    0.10
    æŃ£å¥½
    0.10
     coincide
    0.10
    WARE
    0.10
    èĪĨ论
    0.10
    Activations Density 0.082%

    No Known Activations