© 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. 8127
    Prev
    Next
    INDEX
    Explanations

    Stoker, Dracula, Pack, Boss

    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
    ëĭĪëĭ¤
    -0.10
    轸
    -0.09
    eks
    -0.09
    IFO
    -0.09
    çijľ
    -0.09
    MSN
    -0.09
    ä¸Ģç«Ļ
    -0.09
    uled
    -0.09
    onest
    -0.09
    -Christian
    -0.09
    POSITIVE LOGITS
    dc
    0.08
    aries
    0.08
     tet
    0.08
    ç¯ĩç«ł
    0.08
    sure
    0.08
    缸è¿ŀ
    0.08
    åĬ¿åĬĽ
    0.07
    é¾
    0.07
     Hex
    0.07
    -leaning
    0.07
    Activations Density 0.006%

    No Known Activations