© 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. 48602
    Prev
    Next
    INDEX
    Explanations

    forum posts

    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
    èĽĨ
    -0.09
    Ø·Ùģ
    -0.09
    漩
    -0.08
    æĭį
    -0.08
     Trav
    -0.08
    äºĮåŃĹ
    -0.08
    bis
    -0.08
    طرÙĤ
    -0.08
    鱿
    -0.08
    sWith
    -0.08
    POSITIVE LOGITS
    gere
    0.10
    olle
    0.09
    å°ıå°ı
    0.09
    令
    0.09
    æĬĬè¿Ļ个
    0.08
     Denn
    0.08
    å½ĵæŶ
    0.08
    çķ¶æĻĤ
    0.08
    å·¦åı³
    0.08
    çľĭçĤ¹
    0.08
    Activations Density 0.177%

    No Known Activations