© 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. 21506
    Prev
    Next
    INDEX
    Explanations

    treatment of conditions

    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
    UTH
    -0.10
    ä¸Ģä¸Ŀ
    -0.10
    æĪŁ
    -0.10
     hẹn
    -0.10
    abad
    -0.10
    åĩĭ
    -0.10
    åĩłæŃ¥
    -0.10
    è¾Ń
    -0.10
    æĬĹçĻĮ
    -0.09
    è¾ŀ
    -0.09
    POSITIVE LOGITS
    æłĩåĩĨåĮĸ
    0.09
    /pre
    0.09
    忽çĦ¶
    0.09
    leur
    0.08
    ise
    0.08
    ä¹ĭéģĵ
    0.08
    æ·ĭ
    0.08
    å°ıåĦ¿
    0.08
    åIJĦç±»
    0.08
    éĤ£äºĽ
    0.07
    Activations Density 0.220%

    No Known Activations