© 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. 22147
    Prev
    Next
    INDEX
    Explanations

    under pressure or weight

    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
    è¾Ľ
    -0.09
    æ±ģ
    -0.09
     Jes
    -0.09
    ilater
    -0.09
    太åŃIJ
    -0.09
     ÑģÑĥ
    -0.09
    伶
    -0.09
    人家
    -0.08
    åĩ¡äºĭ
    -0.08
    ár
    -0.08
    POSITIVE LOGITS
    è´Łæĭħ
    0.14
    åĨ²åĩ»
    0.12
    æīĵåĩ»
    0.12
     burden
    0.11
    è´Łèį·
    0.10
     impact
    0.10
    åİĭåĬĽ
    0.10
    æīĵåİĭ
    0.09
    éĩįä»»
    0.09
    åľī
    0.09
    Activations Density 0.069%

    No Known Activations