© 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. 27556
    Prev
    Next
    INDEX
    Explanations

    age or birth and duration

    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
    èĩªè¡Į
    -0.10
    åĿĢ
    -0.09
     Kid
    -0.09
    asu
    -0.09
    ades
    -0.09
    说ä¸įå®ļ
    -0.09
    æ¯ıå¹´
    -0.09
    轨éģĵ
    -0.08
    è¸Ł
    -0.08
    kee
    -0.08
    POSITIVE LOGITS
    åĩºçĶŁ
    0.12
    è¥ģ
    0.11
     Birth
    0.09
    birth
    0.09
    imit
    0.09
    å©´åĦ¿
    0.09
     birth
    0.09
    æľįåĬ¡æľºæŀĦ
    0.09
     Bened
    0.08
    IMIT
    0.08
    Activations Density 0.064%

    No Known Activations