© 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. 22146
    Prev
    Next
    INDEX
    Explanations

    past habitual actions

    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
    åıĤåĬłäºĨ
    -0.11
    ä½ľåĩºäºĨ
    -0.11
    éĢīæĭ©äºĨ
    -0.10
    产çĶŁäºĨ
    -0.10
    éĩĩçĶ¨äºĨ
    -0.10
    ä½ľäºĨ
    -0.10
    èĭ¥å¹²
    -0.10
    缮åīįæŃ£åľ¨
    -0.10
    建ç«ĭäºĨ
    -0.10
    èĬ±äºĨ
    -0.10
    POSITIVE LOGITS
    å°±ä¼ļ
    0.16
    å¾Ģå¾Ģ
    0.15
    便ä¼ļ
    0.14
    ä»ĸä¼ļ
    0.13
    æľīæŶ
    0.13
    å¾Ģå¾Ģä¼ļ
    0.13
    ä»ĸ们ä¼ļ
    0.13
    å°±æľĥ
    0.13
    éĥ½ä¼ļ
    0.13
    æĪijä¼ļ
    0.12
    Activations Density 0.068%

    No Known Activations