© 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. 54707
    Prev
    Next
    INDEX
    Explanations

    loss of life or possessions

    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
    èĮ¹
    -0.10
    æ²»å®ī
    -0.09
     Packet
    -0.09
    INA
    -0.09
    ç¥ģ
    -0.08
    æĭĽèģĺä¿¡æģ¯
    -0.08
    æįķæįī
    -0.08
    ãĥ¨
    -0.08
    éģij
    -0.08
    忤
    -0.08
    POSITIVE LOGITS
    趾
    0.09
    亲人
    0.09
     Bern
    0.08
    é¢ł
    0.08
     (()
    0.08
    ç»ıåİĨäºĨ
    0.08
    zano
    0.08
     direction
    0.08
    æIJŃ
    0.08
    zsche
    0.08
    Activations Density 0.019%

    No Known Activations