© 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. 26933
    Prev
    Next
    INDEX
    Explanations

    sales tax

    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
    ä¸Ģå¤ľ
    -0.09
    ness
    -0.09
    海岸
    -0.09
     Hữu
    -0.09
    cip
    -0.09
    ked
    -0.09
    æĪij们认为
    -0.09
     возд
    -0.09
    éĥľ
    -0.08
    海滩
    -0.08
    POSITIVE LOGITS
    -offs
    0.10
     brisk
    0.10
    isbury
    0.09
    ogg
    0.09
    flare
    0.09
    æĬ¤èº«
    0.09
    caff
    0.09
    æķ¬ä¸ļ
    0.09
    ables
    0.09
    OrUpdate
    0.09
    Activations Density 0.072%

    No Known Activations