© 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. 34465
    Prev
    Next
    INDEX
    Explanations

    tacos or chile variations

    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
    æĭĤ
    -0.09
     Booth
    -0.09
    éħ¸
    -0.09
    海滨
    -0.09
    ë¥ł
    -0.08
    éĽĨè£ħç®±
    -0.08
    åħµåĻ¨
    -0.08
     Dtype
    -0.08
    æĮ¥æīĭ
    -0.08
    æĦıè§ģåıįé¦Ī
    -0.08
    POSITIVE LOGITS
    arde
    0.10
    èĴ¿
    0.10
    quam
    0.09
    lide
    0.09
    sey
    0.09
    ä¸Ģ份
    0.08
    .lift
    0.08
    esar
    0.08
    cence
    0.08
    -highlight
    0.08
    Activations Density 0.003%

    No Known Activations