© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8063
    Prev
    Next
    INDEX
    Explanations

    enactivism or networks or capital

    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
    åĴ¬
    -0.10
    åħįéĻ¤
    -0.10
    ä¸ĢæĬĬ
    -0.09
    è®Ń
    -0.09
    è¾°
    -0.09
    亲åıĭ
    -0.09
    æ·¦
    -0.08
    亲
    -0.08
    fig
    -0.08
    èµ°
    -0.08
    POSITIVE LOGITS
    çłĶ究éĻ¢
    0.11
    ãĤ¹ãĤ¿ãĥ³
    0.10
    èĻİ
    0.10
     Thủ
    0.10
     theory
    0.09
    çIJĨ论
    0.09
    ãģĹãĤĩãģĨ
    0.09
    åľ°éĿ¢
    0.09
     Lover
    0.09
    çIJĨè«ĸ
    0.09
    Activations Density 0.199%

    No Known Activations