© 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. 35815
    Prev
    Next
    INDEX
    Explanations

    pricing and cost details

    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
    æĬµåĪ¶
    -0.09
    iken
    -0.09
    .mem
    -0.09
    anh
    -0.08
    æĭ¼æIJı
    -0.08
    ä¼Ĺ
    -0.08
    读åIJİ
    -0.08
    ipy
    -0.08
    ساء
    -0.08
    æĪĸå°Ĩ
    -0.08
    POSITIVE LOGITS
    иÑĢование
    0.11
    æľºåĪ¶
    0.09
    驸
    0.09
    çŃĸçķ¥
    0.09
    hift
    0.08
     Pound
    0.08
    emodel
    0.08
    à¹īà¸Ńม
    0.08
    ãĤĤãģĨ
    0.08
    åı¦ä¸Ģ
    0.08
    Activations Density 0.018%

    No Known Activations