© 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. 30145
    Prev
    Next
    INDEX
    Explanations

    U.S. senators' names

    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
     Pros
    -0.08
    æĬĹè®®
    -0.08
     grid
    -0.08
    ä¹Łç®Ĺ
    -0.08
    轩
    -0.08
    åĽ´
    -0.08
    æīij
    -0.08
    é²ģè¿ħ
    -0.08
    伤
    -0.08
     Grid
    -0.08
    POSITIVE LOGITS
    _VM
    0.10
    arat
    0.10
     VÅ©
    0.10
    .defaultValue
    0.10
    æļ´éĽ¨
    0.09
    IMIZE
    0.09
    èĿī
    0.09
    åıįæĺł
    0.09
     Millenn
    0.08
    åħ³äºİæĪij们
    0.08
    Activations Density 0.143%

    No Known Activations