© 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. 62085
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
    lando
    -0.11
    寻
    -0.09
    涯
    -0.08
    ipple
    -0.08
    ä»İå°ı
    -0.08
    åĪĨéĶĢ
    -0.08
    å·¡æŁ¥
    -0.08
    _tiles
    -0.07
     Arn
    -0.07
    orca
    -0.07
    POSITIVE LOGITS
    为åķ¥
    0.12
    为ä»Ģä¹Īè¦ģ
    0.11
     certain
    0.10
    çĤºä»Ģ麼
    0.10
    为ä»Ģä¹Ī
    0.10
    æŁIJä¸Ģ
    0.10
    æĢĢæĬ±
    0.10
    为ä½ķ
    0.10
    çļĦä¸ĢåĪĩ
    0.10
    è¿Ļä¹Ī
    0.10
    Activations Density 0.075%

    No Known Activations