© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8423
    Prev
    Next
    INDEX
    Explanations

    piecing up, blocks, stash, using, Copyright, MC

    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
    æijĺ
    -0.10
    å®ģ
    -0.10
    Prem
    -0.09
    å¹½
    -0.09
     Karma
    -0.09
    寧
    -0.09
     Nathan
    -0.09
     Ki
    -0.09
    erman
    -0.09
    ki
    -0.08
    POSITIVE LOGITS
    (es
    0.10
    Margins
    0.10
    razy
    0.09
    enci
    0.09
     Flesh
    0.09
    å¿Ļ
    0.09
    uos
    0.08
    大æ£ļ
    0.08
    /GPL
    0.08
    unken
    0.08
    Activations Density 0.015%

    No Known Activations