© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 291
    Prev
    Next
    INDEX
    Explanations

    barbara

    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
    sWith
    -0.31
    -ahead
    -0.23
    tures
    -0.23
    tos
    -0.21
    ovi
    -0.20
    aro
    -0.20
    ores
    -0.20
    ¼
    -0.20
    erv
    -0.20
    itial
    -0.20
    POSITIVE LOGITS
    ized
    0.29
     же
    0.21
    esco
    0.21
    lest
    0.20
    zimmer
    0.19
    ALLY
    0.18
    竣
    0.18
    burg
    0.18
    ä¸ĩ象
    0.18
    ize
    0.18
    Activations Density 0.015%

    No Known Activations