© 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. 4747
    Prev
    Next
    INDEX
    Explanations

    choose from

    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
    wald
    -0.10
    oris
    -0.10
    лав
    -0.09
    ston
    -0.09
    å¿ĥæĻº
    -0.09
    éļıä¹ĭ
    -0.09
    nap
    -0.09
    uplicates
    -0.09
    jack
    -0.09
    æıIJåĢ¡
    -0.09
    POSITIVE LOGITS
    èĮ«èĮ«
    0.09
    åĩ«
    0.09
    èĮ«
    0.09
    ä¼Ĺå¤ļ
    0.09
     пÑĢоÑĤ
    0.08
     among
    0.08
    ein
    0.08
    ä¼Ĺ
    0.08
     multitude
    0.08
    éĤ£äºĽ
    0.08
    Activations Density 0.008%

    No Known Activations