© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 78
    Prev
    Next
    INDEX
    Explanations

    directory listings and catalogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    Sentence
    -0.26
    Prediction
    -0.26
    AIT
    -0.25
     Prediction
    -0.25
    åģ·
    -0.24
    Jerry
    -0.24
    predicted
    -0.23
    killer
    -0.23
    prediction
    -0.23
    trash
    -0.23
    POSITIVE LOGITS
    åIJįå½ķ
    0.46
     listings
    0.42
    åIJįåįķ
    0.38
    éģįå¸ĥ
    0.38
     searchable
    0.36
     listing
    0.36
     directory
    0.34
    ä¸Ģè§Ī
    0.33
     list
    0.32
     catalog
    0.32
    Activations Density 0.039%

    No Known Activations