© 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. 58286
    Prev
    Next
    INDEX
    Explanations

    our [noun]

    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
    å§Ķå®£ä¼łéĥ¨
    -0.09
    欢è¿İ大家
    -0.09
    å´Ľ
    -0.08
    utta
    -0.08
    stone
    -0.08
    ä¸Ģé¡¿
    -0.08
    ku
    -0.08
    æĢľ
    -0.08
     nowrap
    -0.08
    人éĻħåħ³ç³»
    -0.08
    POSITIVE LOGITS
    缮çļĦæĺ¯
    0.12
    仵
    0.10
     goal
    0.10
    缮æ¨Ļ
    0.10
    /backend
    0.10
     aim
    0.09
    å·¥ä½ľäººåijĺ
    0.09
    aim
    0.09
    erde
    0.09
    åĽ¢éĺŁ
    0.08
    Activations Density 0.028%

    No Known Activations