© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7077
    Prev
    Next
    INDEX
    Explanations

    Formula 1 team

    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
    æ²¹èħ»
    -0.09
    å·ŀåĮº
    -0.08
     USDA
    -0.08
    èµ·åĪ°
    -0.08
    åľ¨æ¸¸æĪıä¸Ń
    -0.08
    Incre
    -0.08
     Morr
    -0.07
    æµ·é²ľ
    -0.07
    hen
    -0.07
     US
    -0.07
    POSITIVE LOGITS
    åı²ä¸Ĭ
    0.11
    zyst
    0.10
    人士
    0.10
    æĺİçıł
    0.10
    ä¸įèĥ½åĨį
    0.10
     Belgi
    0.09
     Attribution
    0.09
    ooks
    0.09
    -ready
    0.09
    erva
    0.09
    Activations Density 0.014%

    No Known Activations