© 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. 3370
    Prev
    Next
    INDEX
    Explanations

    reason why or because

    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
    Authenticated
    -0.09
    _COMMON
    -0.08
    æ¸ħæĸ°
    -0.08
    ìŀ¡
    -0.08
     добÑĢо
    -0.08
    .Common
    -0.08
    preced
    -0.08
    ä¸Ī
    -0.08
    ä¸į顾
    -0.08
    æ¸ħæ´ģ
    -0.08
    POSITIVE LOGITS
    æĺ¯åĽłä¸º
    0.17
    çļĦåİŁåĽł
    0.16
    åİŁåĽł
    0.15
    å°±æĺ¯åĽłä¸º
    0.15
    为ä»Ģä¹Īä¸į
    0.14
    åİŁåĽłæĺ¯
    0.13
    ä¸įæĦ¿æĦı
    0.13
    è¿Łè¿Ł
    0.12
    æľªèĥ½
    0.12
     reasons
    0.12
    Activations Density 0.182%

    No Known Activations