© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2024
    Prev
    Next
    INDEX
    Explanations

    nostalgic, historical, vintage

    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
    æķĪçİĩ
    -0.26
    /workspace
    -0.26
    ouns
    -0.24
     efficiency
    -0.24
    åIJĪä½ľ
    -0.23
     consort
    -0.23
    Stopping
    -0.23
    lip
    -0.23
    èĩªçIJĨ
    -0.23
     stop
    -0.23
    POSITIVE LOGITS
     historical
    0.45
     nostalgic
    0.43
    åİĨåı²
    0.42
    追溯
    0.41
     historic
    0.41
     nostalg
    0.40
    æĤłä¹ħ
    0.40
     vintage
    0.39
    (history
    0.39
    histor
    0.38
    Activations Density 0.189%

    No Known Activations