© 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. 9230
    Prev
    Next
    INDEX
    Explanations

    nice descriptors

    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
    TRS
    -0.10
    ÑĭÑĪ
    -0.09
    еÑĢÑĮ
    -0.09
    ché
    -0.09
    ãģĦãģŁãĤī
    -0.09
    åIJįè¯į
    -0.09
    ä½ľåĵģåĨħ容
    -0.09
    /TR
    -0.09
    รà¸ģ
    -0.09
    åģľæŃ¢
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.11
    ä¸įéĶĻ
    0.10
    稳å®ļçļĦ
    0.10
    -looking
    0.10
    -sized
    0.09
    ä¸įéĮ¯
    0.09
    eners
    0.09
     enough
    0.09
     sized
    0.09
    baum
    0.09
    Activations Density 0.007%

    No Known Activations