© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14472
    Prev
    Next
    INDEX
    Explanations

    forum posts and threads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    acular
    -0.21
    pec
    -0.20
     facts
    -0.20
    Twitter
    -0.19
    qual
    -0.18
     trông
    -0.18
    urdy
    -0.18
    orio
    -0.18
    .twitter
    -0.18
    ECH
    -0.18
    POSITIVE LOGITS
    å¸ĸåŃIJ
    0.46
    论åĿĽ
    0.43
     forum
    0.39
     Forum
    0.36
    forum
    0.36
     ÑĦоÑĢÑĥм
    0.36
     forums
    0.35
    Forum
    0.32
    forums
    0.32
     threads
    0.32
    Activations Density 0.160%

    No Known Activations