© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53236
    Prev
    Next
    INDEX
    Explanations

    ignore or discard

    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
    utt
    -0.10
    æµģåĬ¨æĢ§
    -0.10
    éĹ®è´£
    -0.09
    ãĥĨãĥ¼ãĥŀ
    -0.09
    èĩ´çĶµ
    -0.09
    åħ±äº«
    -0.09
    à¸Ĭะ
    -0.09
    LING
    -0.08
    æĹħ
    -0.08
    è©¢
    -0.08
    POSITIVE LOGITS
    ä¸įçIJĨ
    0.16
    忽çķ¥
    0.12
    åĪĨ辨
    0.12
    ä¸įå±ij
    0.11
    ä¸įäºĪ
    0.11
    ignore
    0.11
    å±ıèĶ½
    0.11
     ignore
    0.11
    å¿įåıĹ
    0.11
    岿
    0.10
    Activations Density 0.083%

    No Known Activations