© 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. 56150
    Prev
    Next
    INDEX
    Explanations

    Nelson, Madden, Cole

    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
    éĴī
    -0.10
    çĨ¨
    -0.09
    åijĺ
    -0.09
    çļĦåķĨåĵģ
    -0.09
    åĵ¡
    -0.09
    åįķ身
    -0.09
    以人为
    -0.08
    çĸ¾
    -0.08
    umi
    -0.08
    wers
    -0.08
    POSITIVE LOGITS
    çĪ¶åŃIJ
    0.13
    家æĹı
    0.12
    åħĦ
    0.11
    ä¸Ģ家
    0.11
    ä¾Ħ
    0.11
     brother
    0.11
     family
    0.11
    çĪ¶
    0.10
     sibling
    0.10
     father
    0.10
    Activations Density 0.099%

    No Known Activations