© 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. 20831
    Prev
    Next
    INDEX
    Explanations

    sanctioned activities and outcomes

    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
    ä¹łæĥ¯
    -0.09
    æĦ§
    -0.09
    hton
    -0.08
    erton
    -0.08
    éĩįä¸Ń
    -0.08
    åıįåĵį
    -0.08
    鸱
    -0.08
    éĻĽä¸ĭ
    -0.08
    æı´åĬ©
    -0.08
    agan
    -0.08
    POSITIVE LOGITS
     vitae
    0.09
    æĮĪ
    0.09
    _union
    0.09
    ãĤ
    0.09
    ä¿Ŀç¨İ
    0.09
    _sb
    0.09
    è´¥
    0.09
    åħ±çĶŁ
    0.09
    olute
    0.08
    PELL
    0.08
    Activations Density 0.011%

    No Known Activations