© 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. 55716
    Prev
    Next
    INDEX
    Explanations

    ro followed by words

    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
     Maj
    -0.09
    enta
    -0.09
    onne
    -0.09
    红åĮħ
    -0.09
    ä¸į管æĺ¯
    -0.09
    osto
    -0.08
     Democrat
    -0.08
    atre
    -0.08
    arl
    -0.08
    ä¸įåıĬ
    -0.08
    POSITIVE LOGITS
     Bakan
    0.09
    å¤Ń
    0.09
    .addRow
    0.09
    åŃIJå¼Ł
    0.09
    è£ģåĪ¤
    0.08
    åĩıéĢŁ
    0.08
    æľīåIJį
    0.08
    поÑĢ
    0.08
    anager
    0.08
    æ´¾
    0.08
    Activations Density 0.029%

    No Known Activations