© 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. 49050
    Prev
    Next
    INDEX
    Explanations

    shell pipe operator

    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
    èĤ¤
    -0.11
    æŃ¥è¡Į
    -0.10
    å°¤
    -0.10
     Kö
    -0.10
     neglig
    -0.10
    ëŀĦ
    -0.09
    踪
    -0.09
     runway
    -0.09
    à¹Ĥà¸Ĭ
    -0.09
     Dominion
    -0.09
    POSITIVE LOGITS
    管éģĵ
    0.11
     Pipes
    0.11
     pipe
    0.11
    Pipe
    0.11
     Pipe
    0.10
    .pipe
    0.10
    _stderr
    0.10
    管
    0.09
    lexport
    0.09
    (pipe
    0.09
    Activations Density 0.205%

    No Known Activations