© 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. 13661
    Prev
    Next
    INDEX
    Explanations

    lifting, reps, sets

    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
    足迹
    -0.21
    ä¸Ģå¤ľ
    -0.21
     Overnight
    -0.20
    è½Ń
    -0.19
    æ¸Ĭ
    -0.19
    æºIJ头
    -0.18
     Pub
    -0.18
     Tok
    -0.18
     dating
    -0.18
    ereo
    -0.18
    POSITIVE LOGITS
    次æķ°
    0.21
    ea
    0.20
     каждого
    0.20
    Odd
    0.19
    layui
    0.18
    å±Ĭ
    0.18
    æľ«
    0.18
    çīĪæĿĥå½Ĵ
    0.18
    åĪĨæĺİ
    0.18
    屿
    0.18
    Activations Density 0.015%

    No Known Activations