© 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. 15370
    Prev
    Next
    INDEX
    Explanations

    compliment and complimentary

    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
    åĽ½ç±į
    -0.20
    oks
    -0.18
    åıijå±ķçIJĨ念
    -0.17
    éĤ¨
    -0.17
    abouts
    -0.17
    pad
    -0.16
    ugin
    -0.16
    æĤ²
    -0.15
    ossa
    -0.15
    åıijå±ķ
    -0.15
    POSITIVE LOGITS
     sake
    0.19
    даÑĢ
    0.19
    sm
    0.18
    shops
    0.17
    alah
    0.17
    èµī
    0.17
    aly
    0.17
    antan
    0.17
    sWith
    0.16
    pu
    0.16
    Activations Density 0.003%

    No Known Activations