© 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. 9963
    Prev
    Next
    INDEX
    Explanations

    data transmission speed

    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
     Leh
    -0.09
    å´ĩ
    -0.08
    PAD
    -0.08
    ä»·åĢ¼éĵ¾
    -0.08
     lá»Ļ
    -0.08
    ä¸Ńç¾İ
    -0.08
    æľīèĩªå·±çļĦ
    -0.08
    _PG
    -0.08
    _codegen
    -0.08
    _ABC
    -0.08
    POSITIVE LOGITS
    éĢŁåº¦
    0.19
     speeds
    0.17
     speed
    0.15
     tá»ijc
    0.15
    éĢŁ
    0.15
    éĢŁçİĩ
    0.15
    éĢŁåº¦å¿«
    0.14
    -speed
    0.14
    é«ĺéĢŁ
    0.14
    speed
    0.14
    Activations Density 0.120%

    No Known Activations