© 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. 11583
    Prev
    Next
    INDEX
    Explanations

    dash / dashed word endings

    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¯åŁº
    -0.18
    大æłij
    -0.17
    缴éĢļ车
    -0.17
    åĹij
    -0.17
    大æĪ·
    -0.17
    ships
    -0.16
    orest
    -0.16
    ocz
    -0.16
    ç¼°
    -0.15
    æ¦Ķ
    -0.15
    POSITIVE LOGITS
    ingly
    0.21
    (es
    0.19
    esModule
    0.17
    注æĦı
    0.17
    aneous
    0.17
    å¥ł
    0.16
    以åħį
    0.16
    ew
    0.16
    ¹
    0.16
    lify
    0.16
    Activations Density 0.007%

    No Known Activations