© 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. 37189
    Prev
    Next
    INDEX
    Explanations

    need assistance

    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
    ä¸į论
    -0.09
    éģĩ
    -0.09
    å±ģ
    -0.09
    ä¸įå°ij人
    -0.09
     Malone
    -0.09
    ãĤ·ãĥ§ãĥĥãĥĹ
    -0.09
     Alvarez
    -0.08
    ä¸įå°ij
    -0.08
    çĩİ
    -0.08
    çĴľ
    -0.08
    POSITIVE LOGITS
    benchmark
    0.12
     assistance
    0.12
    好çľĭ
    0.11
    Benchmark
    0.10
    lessly
    0.10
     benchmark
    0.10
     Assistance
    0.09
    å®īåħ¨ä¿Ŀéļľ
    0.09
     Benchmark
    0.09
    太大
    0.09
    Activations Density 0.025%

    No Known Activations