© 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. 12533
    Prev
    Next
    INDEX
    Explanations

    version or later

    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
    orie
    -0.21
    atte
    -0.20
    åģļå®Į
    -0.19
    oric
    -0.19
    åīįåIJİ
    -0.18
    оÑĢ
    -0.18
    erable
    -0.18
    mr
    -0.17
    éĩĮçļĦ
    -0.17
    race
    -0.17
    POSITIVE LOGITS
    ä¸Ģ缴åĪ°
    0.23
    ãģļãģ£ãģ¨
    0.21
    èªī
    0.20
    à¸ģระà¸Ĺ
    0.20
    车åŃIJ
    0.19
    HING
    0.19
    agem
    0.19
     Till
    0.19
    è¿Ħ
    0.19
    éĵ¤
    0.19
    Activations Density 0.048%

    No Known Activations