© 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. 27399
    Prev
    Next
    INDEX
    Explanations

    date range or 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
    åĸĦ
    -0.10
    ìĬ¬
    -0.10
     пÑĢедоÑģÑĤав
    -0.09
    onium
    -0.09
     SELF
    -0.09
    è°®
    -0.08
    ONS
    -0.08
    .DEBUG
    -0.08
    losure
    -0.08
    .true
    -0.08
    POSITIVE LOGITS
    以å¤ĸ
    0.11
    åľ¨è¿ĩåİ»
    0.10
    è¿ĩåİ»çļĦ
    0.10
    ä»»ä½ķä¸Ģ个
    0.09
     anywhere
    0.09
    uers
    0.09
    çİ°è¡Į
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
     or
    0.09
    ä»»ä½ķ
    0.09
    Activations Density 0.445%

    No Known Activations