© 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. 4961
    Prev
    Next
    INDEX
    Explanations

    recruitment and recruiting

    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
    å¯ĵ
    -0.10
    éģ¿
    -0.09
    åŃ¦å®¶
    -0.09
    æĭį
    -0.09
    å¦ĩ
    -0.08
    å¯ĵæĦı
    -0.08
    æľķ
    -0.08
    磾
    -0.08
    .oc
    -0.08
    rea
    -0.08
    POSITIVE LOGITS
    ä¼ļ计å¸Ī
    0.11
    pled
    0.10
    blas
    0.10
    ç½ijå°ıç¼ĸ
    0.09
    ä¸įåĪ°
    0.09
    ève
    0.09
    è¦ģæĺ¯
    0.09
    apas
    0.09
    éªĬ
    0.09
    æĹĥ
    0.09
    Activations Density 0.020%

    No Known Activations