© 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. 13827
    Prev
    Next
    INDEX
    Explanations

    Ag followed by common suffixes

    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
    entes
    -0.17
    arning
    -0.17
    ry
    -0.17
    egral
    -0.17
    ght
    -0.16
    à¸İ
    -0.16
    ı
    -0.16
    pany
    -0.15
    ģ
    -0.15
    agues
    -0.15
    POSITIVE LOGITS
    ilent
    0.18
    orio
    0.17
    reste
    0.17
    ors
    0.16
    ´
    0.15
    HLT
    0.15
    gregation
    0.15
    æ²ĵ
    0.15
    rib
    0.15
    åīįæīĢ
    0.15
    Activations Density 0.016%

    No Known Activations