© 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. 38972
    Prev
    Next
    INDEX
    Explanations

    raised, upbringing, growing

    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
    æ³Ħ
    -0.09
    麻
    -0.09
    å±ŀäºİèĩªå·±
    -0.08
    ìŀĩ
    -0.08
    è¿ľå¤Ħ
    -0.08
    ãģĮãĤī
    -0.08
    æĿ¥è®¿
    -0.08
    ä¸Ńæłĩ
    -0.08
    æĬ½
    -0.08
    ä¸Ģçľ¼
    -0.08
    POSITIVE LOGITS
    åħ»èĤ²
    0.12
    æĬļåħ»
    0.12
     upbringing
    0.12
    æĪIJéķ¿
    0.12
    raised
    0.12
    çļĦæĪIJéķ¿
    0.11
     Raised
    0.11
     raised
    0.11
     raising
    0.10
    Growing
    0.10
    Activations Density 0.082%

    No Known Activations