© 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. 22225
    Prev
    Next
    INDEX
    Explanations

    oil prices

    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
    è¾ĥ好çļĦ
    -0.10
    å¸ľ
    -0.10
    è¾ĥ好
    -0.10
    è¾ĥ强
    -0.09
    å¼ĢéŨ
    -0.09
     بد
    -0.09
    äºĨä¸ĢäºĽ
    -0.09
     hơi
    -0.09
     Rhode
    -0.09
     gaz
    -0.09
    POSITIVE LOGITS
    HL
    0.09
    ais
    0.08
    款
    0.08
    CTL
    0.08
    лиÑĤ
    0.08
    elman
    0.08
    æŧ
    0.07
     pont
    0.07
    rama
    0.07
    ski
    0.07
    Activations Density 0.023%

    No Known Activations