© 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. 56278
    Prev
    Next
    INDEX
    Explanations

    down to

    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
    LETTE
    -0.10
    éķ¦
    -0.10
    å§Ķç»Ħç»ĩ
    -0.10
    iosis
    -0.10
    ç»ij
    -0.10
    æī¹åıij
    -0.09
    鸿
    -0.09
    ãĤį
    -0.09
    æ²¾
    -0.09
    OTAL
    -0.09
    POSITIVE LOGITS
     whether
    0.11
    åıªåī©
    0.10
    è¦ģä¸įè¦ģ
    0.10
    å¦Ĥä½ķçľĭå¾ħ
    0.10
    è¦ģä¹Ī
    0.10
    åıªåī©ä¸ĭ
    0.09
     core
    0.09
     two
    0.09
    ä¸Ģåı¥è¯Ŀ
    0.09
    bow
    0.08
    Activations Density 0.012%

    No Known Activations