© 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. 2288
    Prev
    Next
    INDEX
    Explanations

    useful information

    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
    uded
    -0.22
    污
    -0.21
    ï¸ı
    -0.21
    wards
    -0.21
     successfully
    -0.21
    主æŨ
    -0.20
    -mounted
    -0.20
    /groups
    -0.20
    å¼ıçļĦ
    -0.20
     ÑĥÑģпеÑĪ
    -0.20
    POSITIVE LOGITS
     ÃŃch
    0.28
    /help
    0.28
    ness
    0.23
    NESS
    0.23
    åİŁæĸĩåľ°åĿĢ
    0.23
     bagi
    0.23
    -looking
    0.22
    /use
    0.22
    åĵī
    0.22
    ä¸İåIJ¦
    0.22
    Activations Density 0.036%

    No Known Activations