© 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. 20416
    Prev
    Next
    INDEX
    Explanations

    admission or entry

    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
    æ³ķå¾ĭ责任
    -0.09
    udeau
    -0.09
     sẵn
    -0.09
    履约
    -0.09
    éľģ
    -0.09
    趸
    -0.09
    åĬłæ²¹
    -0.09
    _mappings
    -0.09
    _IMPLEMENT
    -0.09
    å¤ļå±Ĥ次
    -0.09
    POSITIVE LOGITS
     entry
    0.16
     вÑħод
    0.14
    åħ¥åĽŃ
    0.14
    è¿Ľåħ¥
    0.14
    åħ¥åľº
    0.13
     entrance
    0.13
     admission
    0.12
    è¿ĽéŨ
    0.12
    éĢ²åħ¥
    0.12
    è¿Ľåĩº
    0.12
    Activations Density 0.070%

    No Known Activations