© 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. 29937
    Prev
    Next
    INDEX
    Explanations

    reach itcaregivers adherent

    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
    ä¾ł
    -0.10
    åİļåİļ
    -0.09
    é²Ľ
    -0.09
    æİ°
    -0.09
    çĪ±ä½ł
    -0.09
    è´½
    -0.09
    亿ä¸ĩ
    -0.08
    æĬķå½±
    -0.08
    读æĩĤ
    -0.08
    笼罩
    -0.08
    POSITIVE LOGITS
    åįĩ
    0.10
    游çİ©
    0.09
    æĶ»çķ¥
    0.09
    æĽ³
    0.09
    ä½ĵåĬĽ
    0.08
    è¿ŀ
    0.08
    åİ¿éķ¿
    0.08
    å°ıç¼ĸ
    0.08
    工夫
    0.08
    æķĻç¨ĭ
    0.08
    Activations Density 0.147%

    No Known Activations