© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1092
    Prev
    Next
    INDEX
    Explanations

    convert files or data formats

    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
     pinned
    -0.23
     Sporting
    -0.23
    大å®ĹåķĨåĵģ
    -0.23
    寰
    -0.23
    LinkedIn
    -0.23
    esk
    -0.22
    Spoiler
    -0.22
    Latin
    -0.22
    goals
    -0.22
    pins
    -0.22
    POSITIVE LOGITS
     Converter
    0.42
     conversion
    0.38
     Conversion
    0.37
     converter
    0.36
    转æį¢
    0.35
    Converter
    0.33
     convert
    0.32
     Convert
    0.31
    conversion
    0.31
     converts
    0.29
    Activations Density 0.035%

    No Known Activations