© 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. 15772
    Prev
    Next
    INDEX
    Explanations

    royal names with roman numerals

    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
    ilon
    -0.21
    èĮĹ
    -0.20
    è¿Ļ个è¡Įä¸ļ
    -0.20
    æķ´æķ´
    -0.20
    äºijéĽĨ
    -0.19
    ç¾¹
    -0.19
    åĹ½
    -0.19
    æ°´éĩı
    -0.19
    积æŀģæݨåĬ¨
    -0.19
    缸æ¯Ķ
    -0.18
    POSITIVE LOGITS
    axios
    0.20
    isms
    0.20
    uchos
    0.19
    ioms
    0.19
    linky
    0.18
    olley
    0.18
     Celsius
    0.17
    沿海
    0.17
    spath
    0.17
    asser
    0.17
    Activations Density 0.067%

    No Known Activations