© 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. 6698
    Prev
    Next
    INDEX
    Explanations

    social fabric and life

    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
    åĪ«äºº
    -0.10
    å¹³åĿ¦
    -0.09
    çł£
    -0.09
    hait
    -0.09
    å´ĩæĭľ
    -0.09
    _ie
    -0.08
    ancell
    -0.08
     ÑĥдаÑĢ
    -0.08
    è¿¢
    -0.08
    atr
    -0.08
    POSITIVE LOGITS
    æĹ¥å¸¸çĶŁæ´»
    0.10
    çĶŁæ´»ä¸Ń
    0.10
    æ´»åĬ¨
    0.09
    å½ĵåľ°æĶ¿åºľ
    0.09
     society
    0.09
    åĬĽ
    0.09
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.09
    çİ°å®ŀçĶŁæ´»
    0.09
    åĪ¶è®¢
    0.08
    .getvalue
    0.08
    Activations Density 0.052%

    No Known Activations