© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20100
    Prev
    Next
    INDEX
    Explanations

    encouraged/urged/asked to

    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
    ä¾µèļĢ
    -0.09
    æ±īåŃIJ
    -0.09
    åĽĽæĸ¹
    -0.09
    æĪij们è¦ģ
    -0.09
    çijķ
    -0.09
    åĻ¨æ¢°
    -0.09
    cheme
    -0.09
    ãģķãģĽãģ¦
    -0.09
    azo
    -0.09
     Ñģебе
    -0.08
    POSITIVE LOGITS
    åľ¨æĪijçļĦ
    0.08
    mour
    0.08
    èĩªæĦ¿
    0.08
    ilde
    0.08
    _SLEEP
    0.08
    ç¯Ŀ
    0.08
    atti
    0.08
     att
    0.08
     vol
    0.08
    edian
    0.08
    Activations Density 0.025%

    No Known Activations