© 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. 7876
    Prev
    Next
    INDEX
    Explanations

    shipping to destinations

    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
     wom
    -0.10
    ä¸Ģæŀļ
    -0.10
    å¤
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    ä¸ļ
    -0.09
     Pompe
    -0.08
    rift
    -0.08
    stro
    -0.08
     brushes
    -0.08
     LIFE
    -0.08
    POSITIVE LOGITS
     destinations
    0.22
    缮çļĦåľ°
    0.20
     destination
    0.17
    .destination
    0.17
    dest
    0.16
    destination
    0.15
    (destination
    0.15
     Destination
    0.14
    _DEST
    0.14
    Destination
    0.14
    Activations Density 0.075%

    No Known Activations