© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15166
    Prev
    Next
    INDEX
    Explanations

    public ID

    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
    aram
    -0.21
     ch
    -0.19
     gn
    -0.18
     Arte
    -0.18
    åıĤ
    -0.18
    ott
    -0.18
    itr
    -0.18
    åĪ°æĿ¥
    -0.18
    аÑĢам
    -0.18
    ãģ§ãģĻãĤĪ
    -0.17
    POSITIVE LOGITS
    åİļ
    0.25
    æĭ¢
    0.20
    åı¦å¤ĸ
    0.18
     Thickness
    0.18
    phin
    0.18
    ÑĤÑĢÑĥд
    0.18
     Klo
    0.18
    .datab
    0.18
    undler
    0.18
     bunch
    0.17
    Activations Density 0.451%

    No Known Activations