© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 15983
    Prev
    Next
    INDEX
    Explanations

    lists of options or details

    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
     fkk
    -0.22
    /animations
    -0.21
    ombo
    -0.21
    .archive
    -0.20
    CloseOperation
    -0.20
    OfString
    -0.20
    ivors
    -0.19
    è¿Ļä»¶
    -0.19
    /locale
    -0.19
     viz
    -0.19
    POSITIVE LOGITS
    æ¯ı个
    0.28
    æłı缮
    0.27
    Each
    0.27
     каждой
    0.26
     каждого
    0.25
    ç¿Ķ
    0.25
    éħįæľī
    0.25
    详ç»Ĩ
    0.24
     each
    0.24
    åİĨ代
    0.24
    Activations Density 0.043%

    No Known Activations