© 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. 37783
    Prev
    Next
    INDEX
    Explanations

    -ref

    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
    Lon
    -0.09
    GLOBALS
    -0.08
    aco
    -0.08
    .JPG
    -0.08
    /license
    -0.08
    ä¹Łè®¸æĺ¯
    -0.08
    isz
    -0.08
    .Misc
    -0.08
    omba
    -0.08
    uggle
    -0.08
    POSITIVE LOGITS
    éĤ¯
    0.10
    泡泡
    0.09
    æľĢå¤ļçļĦ
    0.09
    -ref
    0.09
    äºĶä¸Ģ
    0.08
    åĨħ马
    0.08
    å¹Į
    0.08
    åĨįå¤ļ
    0.08
    èĤĩ
    0.08
    ढ
    0.08
    Activations Density 0.114%

    No Known Activations