© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8352
    Prev
    Next
    INDEX
    Explanations

    way or direction

    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
    æĽ´è¦ģ
    -0.10
    æĽ´æľī
    -0.10
    çģµæĦŁ
    -0.09
    inges
    -0.09
    åIJĦèĩª
    -0.09
     завод
    -0.09
    æĽ´
    -0.09
    éĩĮéĿ¢çļĦ
    -0.08
    åIJİéĿ¢çļĦ
    -0.08
    ucci
    -0.08
    POSITIVE LOGITS
     Sink
    0.09
     toward
    0.09
    åij½è¿IJ
    0.09
    岿
    0.09
    avax
    0.08
    çļĦåij½è¿IJ
    0.08
    çµĦ
    0.08
    ç¶ļãģįãĤĴèªŃãĤĢ
    0.08
     напÑĢав
    0.08
    åºŃ
    0.08
    Activations Density 0.028%

    No Known Activations