© 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. 20621
    Prev
    Next
    INDEX
    Explanations

    missing context

    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
    å¯Ĥå¯ŀ
    -0.09
    Messenger
    -0.09
    fts
    -0.09
    ores
    -0.09
    oload
    -0.08
    ắn
    -0.08
    chest
    -0.08
    ETS
    -0.08
    .tim
    -0.08
     @@
    -0.08
    POSITIVE LOGITS
    éĶ´
    0.11
    endum
    0.11
    缺
    0.10
    äºĽä»Ģä¹Ī
    0.10
    lust
    0.10
     missing
    0.09
    ellaneous
    0.09
    /Internal
    0.09
    è¯ģ件
    0.09
    äºĨä¸ĢäºĽ
    0.09
    Activations Density 0.034%

    No Known Activations