© 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. 48927
    Prev
    Next
    INDEX
    Explanations

    McMahon or McConnell and bourbon

    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
    -0.16
    éĻĮ
    -0.11
    è²Į
    -0.10
    mites
    -0.10
    äºĽè®¸
    -0.10
    æĽ³
    -0.10
    acters
    -0.09
    è¿Ļ两
    -0.08
    è¾ĩ
    -0.08
    AAD
    -0.08
    POSITIVE LOGITS
    isse
    0.10
    моÑĤ
    0.10
    ä¸įäºĨ
    0.09
    ists
    0.09
    ame
    0.08
    ãĤĬ
    0.08
    ooter
    0.08
     chặt
    0.08
    InView
    0.08
    å°±æĺ¯è¿Ļæł·
    0.08
    Activations Density 0.003%

    No Known Activations