© 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. 17815
    Prev
    Next
    INDEX
    Explanations

    every/all/each

    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
    å¾Ļ
    -0.10
    ä»Ĭ
    -0.10
    åıªä¼ļ
    -0.09
    æĶ¹æŃ£
    -0.09
    æĭĽ
    -0.09
    è¯ļ
    -0.09
    çķĮ
    -0.09
    зе
    -0.08
    æĻŁ
    -0.08
    ÐľÐIJ
    -0.08
    POSITIVE LOGITS
     every
    0.13
    åı¯çĸij
    0.13
    every
    0.13
    åĩłä¹İ
    0.12
    人人éĥ½
    0.12
    æĪĸå¤ļæĪĸå°ij
    0.11
    æ¯ıä¸Ģ个
    0.11
    Every
    0.11
    åĩłä¹İæīĢæľī
    0.11
    æ¯
    0.10
    Activations Density 0.137%

    No Known Activations