© 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. 63135
    Prev
    Next
    INDEX
    Explanations

    in his

    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
    Cs
    -0.09
    ks
    -0.09
    æĹ¥åIJİ
    -0.08
     Luo
    -0.08
     ÙĪبÙĬÙĨ
    -0.08
     дал
    -0.08
    agne
    -0.08
    主æĦı
    -0.08
     printer
    -0.08
    esting
    -0.08
    POSITIVE LOGITS
    éĻIJ度
    0.12
    çĸµ
    0.11
    äºĨèĩªå·±çļĦ
    0.10
    å®Ŀè´µçļĦ
    0.10
    æĢ¥åī§
    0.09
    mare
    0.09
    åĪĨå¸ĥåľ¨
    0.09
    ongyang
    0.09
    ertools
    0.09
    .jms
    0.09
    Activations Density 0.016%

    No Known Activations