© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9439
    Prev
    Next
    INDEX
    Explanations

    e-mail content and communication

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    æĺİæľĹ
    -0.09
     Tos
    -0.09
    çĶ¨è½¦
    -0.08
    bero
    -0.08
    迹
    -0.08
    _locals
    -0.08
    bek
    -0.08
    bial
    -0.08
    æīĢè°ĵ
    -0.08
    POSITIVE LOGITS
    ÑĪка
    0.09
    媳
    0.09
    éªł
    0.09
    饽
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.08
    æ·ĺ
    0.08
    .pkg
    0.08
    istine
    0.08
    .erb
    0.08
    å°ij
    0.08
    Activations Density 0.364%

    No Known Activations