© 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. 63059
    Prev
    Next
    INDEX
    Explanations

    cigarette smoking and sales

    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
    iegel
    -0.10
    еÑĨ
    -0.10
    owanie
    -0.10
    íħį
    -0.09
    æĢ§çĸ¾çĹħ
    -0.09
    chaft
    -0.09
    ém
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    ãĤĪãģı
    -0.09
    éªĸ
    -0.09
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.10
    æĿ¥ä¸įåıĬ
    0.09
    INAL
    0.09
    bai
    0.08
    çĽĴ
    0.08
    械
    0.08
    inals
    0.08
    ÙħÙĬر
    0.08
    vis
    0.08
    è¢ħ
    0.08
    Activations Density 0.006%

    No Known Activations