© 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. 27929
    Prev
    Next
    INDEX
    Explanations

    adult participants

    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
    为æĬĵ
    -0.10
    åı¯ä»¥çĽ´æİ¥
    -0.09
    æIJ¦
    -0.09
    -tooltip
    -0.09
    被æĬĵ
    -0.09
    äºĶå®ĺ
    -0.09
    çķĻè¨ĢæĿ¿
    -0.08
    ä¸ĢçĶŁ
    -0.08
    ÑĤиÑĢов
    -0.08
     flop
    -0.08
    POSITIVE LOGITS
    è·ĥ
    0.10
    åĪĨæĪIJ
    0.09
    å¥ģ
    0.08
    å¹½
    0.08
    çŀ¬
    0.08
     Carly
    0.08
    ally
    0.08
    pring
    0.08
    çĩ¥
    0.08
    æĽĻåħī
    0.08
    Activations Density 0.333%

    No Known Activations