© 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. 55300
    Prev
    Next
    INDEX
    Explanations

    Formula 1 racing

    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
    lege
    -0.09
     Swords
    -0.09
    å®īå®ļ
    -0.09
     Cooler
    -0.09
    lasses
    -0.08
    æĿ¾å¼Ľ
    -0.08
    éĻ¢åŃIJ
    -0.08
     Trudeau
    -0.08
    çģ¯çģ«
    -0.08
    äºĶå®ĺ
    -0.08
    POSITIVE LOGITS
    èµĽè½¦
    0.10
    åIJ¸
    0.09
    åĬĽäºī
    0.09
    åij¼å£°
    0.09
    èį»
    0.09
    è²Įä¼¼
    0.09
    è°Īè°Ī
    0.08
     Sir
    0.08
    Periph
    0.08
    Č↵
    0.08
    Activations Density 0.138%

    No Known Activations