© 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. 37884
    Prev
    Next
    INDEX
    Explanations

    progress and forward movement

    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
    纵横
    -0.10
    çĺ¾
    -0.10
    æĢİä¹Ī说
    -0.10
    ç»Īç»ĵ
    -0.09
    å¸ħ
    -0.09
    èµĸ以
    -0.09
    æĬ¢æĬĵ
    -0.09
     пеÑĢи
    -0.09
    .swagger
    -0.09
    ium
    -0.09
    POSITIVE LOGITS
    çļĦæŃ¥ä¼IJ
    0.11
    èĦļæŃ¥
    0.11
    ToFront
    0.10
    çļĦèĦļæŃ¥
    0.10
    ä¸ĢæŃ¥
    0.10
    æŃ¥ä¼IJ
    0.09
     далÑĮÑĪе
    0.09
    (progress
    0.09
     progress
    0.09
    çĨĻ
    0.09
    Activations Density 0.089%

    No Known Activations