© 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. 23687
    Prev
    Next
    INDEX
    Explanations

    make a living

    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
    ä½£
    -0.10
    inate
    -0.09
    æĥĨ
    -0.09
    便äºİ
    -0.08
    ä¸ĵå±ŀ
    -0.08
     correctly
    -0.08
    èĮ±
    -0.08
    -0.08
    好åIJĥ
    -0.08
     Vict
    -0.08
    POSITIVE LOGITS
    害
    0.10
    ãĤ¹ãĥŀ
    0.10
    ìĶ¨
    0.10
    екÑĤоÑĢ
    0.09
     fortune
    0.09
     livelihood
    0.09
    olean
    0.09
    à¸ģา
    0.09
    导读
    0.09
    sphere
    0.09
    Activations Density 0.065%

    No Known Activations