© 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. 31456
    Prev
    Next
    INDEX
    Explanations

    so ... that

    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
    знаком
    -0.10
    ä¸įå°½
    -0.09
     INCLUDED
    -0.09
    çĨŁæĤīçļĦ
    -0.09
    lik
    -0.09
    dden
    -0.09
    ä¸Ģ大åłĨ
    -0.09
     Cree
    -0.09
     Spicer
    -0.09
    STER
    -0.08
    POSITIVE LOGITS
    以èĩ³äºİ
    0.12
    åıįèĢĮ
    0.09
    åı¯ä»¥è¯´æĺ¯
    0.09
     almost
    0.09
    æģ¨ä¸įå¾Ĺ
    0.09
    åĩłä¹İ没æľī
    0.09
    ç¯Ļ
    0.08
    å°±è¿ŀ
    0.08
    æĹłæ³ķ
    0.08
    ä¸ĢåĪ»
    0.08
    Activations Density 0.026%

    No Known Activations