© 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. 38248
    Prev
    Next
    INDEX
    Explanations

    cling, onto, to

    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
    ฯ
    -0.10
    æľºåħ³
    -0.08
    थ
    -0.08
    ä¹İ
    -0.08
    容
    -0.08
    strt
    -0.08
    urred
    -0.08
    mare
    -0.08
    imore
    -0.08
    izens
    -0.08
    POSITIVE LOGITS
    è¿Ļ份
    0.13
    ä½ıäºĨ
    0.12
    éĤ£ä»½
    0.12
    ä¸įèĪį
    0.10
    念
    0.09
    éĺĦ
    0.09
    nant
    0.09
    ä¸įä½ı
    0.09
    enant
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    Activations Density 0.006%

    No Known Activations