© 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. 15260
    Prev
    Next
    INDEX
    Explanations

    website urls

    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
    çļĦè¿ĽæŃ¥
    -0.21
    furt
    -0.20
    ulla
    -0.19
    anca
    -0.19
    ä¸Ģä¸Ģ
    -0.18
    çŃ¾çº¦
    -0.18
    lez
    -0.18
    éĢIJä¸Ģ
    -0.17
    kker
    -0.17
     Sisters
    -0.17
    POSITIVE LOGITS
    æĬ«
    0.20
    çłī
    0.19
    ubi
    0.18
    ALLY
    0.18
    ta
    0.18
     grind
    0.17
    媵
    0.17
     mate
    0.17
     heap
    0.17
    åħĢ
    0.17
    Activations Density 0.004%

    No Known Activations