© 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. 19640
    Prev
    Next
    INDEX
    Explanations

    awakening

    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®ļäºĨ
    -0.11
    rics
    -0.10
    éĻħ
    -0.08
    ebp
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    tain
    -0.08
    ä¸į解
    -0.08
    ãģĵãģĨ
    -0.08
    ç«ł
    -0.08
    ç¾ģ
    -0.08
    POSITIVE LOGITS
    èĽ°
    0.12
    çĴł
    0.11
     dormant
    0.11
    客æĪ·éľĢæ±Ĥ
    0.11
    é©·
    0.10
     khá»ıi
    0.10
    人们对
    0.10
    æĥº
    0.10
    éĨĴäºĨ
    0.10
    åħįéĻ¤
    0.10
    Activations Density 0.166%

    No Known Activations