© 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. 54508
    Prev
    Next
    INDEX
    Explanations

    special characters and Umlauts

    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
    骥
    -0.10
    åīĸ
    -0.10
    è¾ĩ
    -0.10
    æ¬
    -0.10
    osen
    -0.09
    æĸ°ä¸ī
    -0.09
    ä»Ģä¹Īéĥ½
    -0.09
    agner
    -0.09
    æıĸ
    -0.09
    lsen
    -0.08
    POSITIVE LOGITS
    åģ¥åħ¨
    0.09
    åħ¥åºĵ
    0.09
    æł¹æºIJ
    0.09
    横
    0.09
    å®ĮåĸĦçļĦ
    0.09
    被æīĵ
    0.08
    _frm
    0.08
    Milliseconds
    0.08
    å°ĸ
    0.08
    涧
    0.08
    Activations Density 0.075%

    No Known Activations