© 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. 13277
    Prev
    Next
    INDEX
    Explanations

    prime, odd, and even numbers

    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
    éĻĦå±ŀ
    -0.21
     swing
    -0.20
    {text
    -0.18
    pond
    -0.18
    iese
    -0.17
    Sou
    -0.17
    lessly
    -0.17
    /respond
    -0.17
    press
    -0.17
    reeze
    -0.17
    POSITIVE LOGITS
    decltype
    0.21
    /non
    0.20
    éªħ
    0.19
    -hearted
    0.19
    åĪ¤å®ļ
    0.19
    éªIJ
    0.19
    éħĬ
    0.19
    ä¸İåIJ¦
    0.19
    æĽī
    0.19
    indicator
    0.19
    Activations Density 0.246%

    No Known Activations