© 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. 1084
    Prev
    Next
    INDEX
    Explanations

    $modal, $scope, $http, $select

    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
    rette
    -0.11
    åģļäºĭ
    -0.09
    被æĬĵ
    -0.09
    è¿ĩå¹´
    -0.09
    转åĬ¨
    -0.09
     Hoch
    -0.08
    estation
    -0.08
    ested
    -0.08
    竣工
    -0.08
    .TryParse
    -0.08
    POSITIVE LOGITS
    аÑĢаÑĤ
    0.09
    å¼ĥ
    0.09
    æĺĤ
    0.08
    çļĦæīĭ
    0.08
    umat
    0.08
    ᾶ
    0.08
    Compose
    0.08
    驾
    0.08
    èĬ¹
    0.08
    amental
    0.08
    Activations Density 0.182%

    No Known Activations