© 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. 38598
    Prev
    Next
    INDEX
    Explanations

    modern subjects

    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
    .Marshal
    -0.09
    âĩ¦
    -0.09
    erchant
    -0.09
     обÑĬÑıвл
    -0.09
    uzzi
    -0.09
    ÑĤол
    -0.08
    å¦Ĥæľī
    -0.08
    åIJĦå¼ıåIJĦæł·
    -0.08
    ä¸Ģ身
    -0.08
    anners
    -0.08
    POSITIVE LOGITS
    çݰ代
    0.11
     modern
    0.10
    è¿ij代
    0.10
    ä»Ĭ天çļĦ
    0.09
    åīį身
    0.09
    çļĦ第ä¸Ģ个
    0.09
    ignum
    0.09
     Modern
    0.09
    éħĮ
    0.09
    çı¾ä»£
    0.09
    Activations Density 0.875%

    No Known Activations