© 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. 48731
    Prev
    Next
    INDEX
    Explanations

    Guinness Book of World Records distinction

    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
    lian
    -0.10
     обÑģлÑĥжива
    -0.09
    æ´Ĺæīĭ
    -0.09
    Instance
    -0.09
    .syntax
    -0.09
    æŃī
    -0.09
     INSTANCE
    -0.09
    emann
    -0.09
    éĿłè¿ij
    -0.09
    lord
    -0.09
    POSITIVE LOGITS
    éĩįä»»
    0.13
    èį£èªī
    0.13
    åħīèį£
    0.11
    é¦ĸä½į
    0.11
     responsibility
    0.10
    åIJįèªī
    0.10
     task
    0.10
    主ä½ĵ责任
    0.10
     distinction
    0.10
    æ®Ĭ
    0.09
    Activations Density 0.077%

    No Known Activations