© 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. 11083
    Prev
    Next
    INDEX
    Explanations

    olive oil

    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
    æĸ¯é¡¿
    -0.26
    .rpm
    -0.21
    ä¸įæĿ¥
    -0.20
    对å¤ĸå¼ĢæĶ¾
    -0.20
    amping
    -0.19
    滦
    -0.18
     Brew
    -0.18
    icals
    -0.18
    /material
    -0.18
    辫
    -0.18
    POSITIVE LOGITS
    åĵģè´¨
    0.21
    çĶ¨éĢĶ
    0.20
    两ç§į
    0.20
    AZE
    0.20
    åĿĬ
    0.19
    aze
    0.19
    éľľ
    0.18
     Aviv
    0.18
    æĪij家
    0.18
    use
    0.18
    Activations Density 0.005%

    No Known Activations