© 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. 2329
    Prev
    Next
    INDEX
    Explanations

    programming function calls

    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
    éľīç´ł
    -0.10
    æĮ£
    -0.09
    nette
    -0.09
    æľ¦
    -0.09
    举
    -0.09
    æľīåIJį
    -0.09
    å±¥èģĮ
    -0.09
    çĿ£
    -0.09
    åѦåŃIJ
    -0.08
    keley
    -0.08
    POSITIVE LOGITS
    ‘s
    0.09
    çŃī缸åħ³
    0.09
    è¿Ļä¸Ģ
    0.09
    è¿Ļ个è¯į
    0.08
    åľ¨è¿Ļç§į
    0.08
    çļĦ缮çļĦ
    0.08
    поÑĤ
    0.08
     statements
    0.08
     Joh
    0.08
    èľĪ
    0.08
    Activations Density 1.399%

    No Known Activations