© 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. 48794
    Prev
    Next
    INDEX
    Explanations

    native/fluent language speakers

    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
    æ¢Ĺ
    -0.10
    åĻ¨
    -0.09
    è¿ŁåĪ°
    -0.08
    egt
    -0.08
    äºĮèĢħ
    -0.08
    è¿Ķ
    -0.08
    ucle
    -0.08
    _far
    -0.08
    -bordered
    -0.08
     elong
    -0.08
    POSITIVE LOGITS
    /native
    0.11
    nat
    0.10
    å¤ĸè¯Ń
    0.10
    åĽ½ç±į
    0.10
    èĥ¶
    0.10
     flu
    0.10
     fluent
    0.10
    çĶŁæ´»åľ¨
    0.10
     ÑĢож
    0.09
     nat
    0.09
    Activations Density 0.116%

    No Known Activations