© 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. 9183
    Prev
    Next
    INDEX
    Explanations

    duration or interval

    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
    ilt
    -0.09
    ä¹Ķ
    -0.09
    éļĶ
    -0.09
     sơ
    -0.08
     mell
    -0.08
    ãĥķãĤ§
    -0.08
    ibi
    -0.08
    åıįæŃ£
    -0.08
    ILT
    -0.08
    çĭ¬åħ·
    -0.08
    POSITIVE LOGITS
    çīĩåĪ»
    0.18
    çŁŃæļĤ
    0.12
    ä¸Ģä¼ļåĦ¿
    0.11
    ä¸Ģä¼ļ
    0.11
    çľ¼åīį
    0.10
    ä¸Ģé¡¿
    0.10
    åįķ纯
    0.10
    ä¸ĢåĪ»
    0.10
     briefly
    0.10
    igrations
    0.09
    Activations Density 0.173%

    No Known Activations