© 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. 33656
    Prev
    Next
    INDEX
    Explanations

    did, is, they, it, there, you

    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
    è¿Ļæł·åģļ
    -0.11
    ling
    -0.10
    è¿Ļä¹Īåģļ
    -0.10
     Ting
    -0.08
    åĽ½æľīèµĦ产
    -0.08
    沧
    -0.08
     пÑĢÑı
    -0.08
    æŃ¤ä¸¾
    -0.08
    _inputs
    -0.08
     kut
    -0.08
    POSITIVE LOGITS
    åıĭæĥħ
    0.10
    妥
    0.08
    å¿ĥæĻº
    0.08
     Snyder
    0.08
     FP
    0.08
    ained
    0.08
    èĢĮä¸Ķ
    0.08
    ps
    0.08
    gie
    0.08
    è¯Ŀè¯ŃæĿĥ
    0.08
    Activations Density 0.035%

    No Known Activations