© 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. 47961
    Prev
    Next
    INDEX
    Explanations

    son or daughter

    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
    äºĨèĩªå·±çļĦ
    -0.10
    ãģĦãģĨ
    -0.10
    女士
    -0.09
    èĮ«èĮ«
    -0.09
     herself
    -0.09
    äºĨä¸Ģ个
    -0.09
    mente
    -0.09
    è¨ĢãģĪãģ°
    -0.09
     ÙĨÙģسÙĩا
    -0.09
    ÑģÑĤÑĮ
    -0.09
    POSITIVE LOGITS
    ftware
    0.13
    itto
    0.10
    orous
    0.10
    ntag
    0.10
    rne
    0.10
    ification
    0.10
    nets
    0.09
    媳å¦ĩ
    0.09
    omial
    0.09
    -called
    0.09
    Activations Density 0.020%

    No Known Activations