© 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. 58457
    Prev
    Next
    INDEX
    Explanations

    proximity and access

    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
    éĹ¨æ§Ľ
    -0.10
    ä¾Ŀ
    -0.10
    ä¸įåħ¬å¹³
    -0.09
    ipe
    -0.09
    ucht
    -0.09
     Borders
    -0.09
    严éĩį
    -0.09
    ope
    -0.09
    åºĹéĩĮ
    -0.08
     canadian
    -0.08
    POSITIVE LOGITS
    çĦķ
    0.10
    访
    0.09
    æŀī
    0.09
    arend
    0.09
    å¸Ń
    0.08
    ail
    0.08
    梦è§ģ
    0.08
     scooter
    0.08
    çĪ½
    0.08
    æĹ¥æĬ¥
    0.08
    Activations Density 0.017%

    No Known Activations