© 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. 6512
    Prev
    Next
    INDEX
    Explanations

    childhood memories and growing up

    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
    夫å¦ĩ
    -0.09
    ä¸Ģå¹´å¤ļ
    -0.08
     Pall
    -0.08
    è·º
    -0.08
    èµĿ
    -0.08
     major
    -0.08
    æ¼Ĩ
    -0.08
    ä¸ĢåĿĹ
    -0.08
     Schiff
    -0.08
     Cursor
    -0.08
    POSITIVE LOGITS
    å°ıæŶåĢĻ
    0.24
    童年
    0.22
     childhood
    0.20
     Childhood
    0.16
    å½ĵå¹´
    0.14
    ä»İå°ıå°±
    0.12
    å°ıåѦ
    0.12
    ä»İå°ı
    0.12
    ä¸Ĭä¸ĸ纪
    0.11
    ç»ıåİĨè¿ĩ
    0.11
    Activations Density 0.132%

    No Known Activations