© 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. 15109
    Prev
    Next
    INDEX
    Explanations

    based on book or novel

    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
     Appearance
    -0.19
    çݩ家æľĭåıĭ
    -0.19
    æīª
    -0.19
    åĪ©äºļ
    -0.18
     Transcript
    -0.18
     над
    -0.18
    appeared
    -0.18
     оÑĦиÑģ
    -0.18
    ä¸ĢéĿ¢
    -0.18
    éĹ²
    -0.18
    POSITIVE LOGITS
    åİŁèijĹ
    0.31
    æĶ¹ç¼ĸ
    0.24
    æķħäºĭ
    0.21
    åİŁæĸĩ
    0.20
    bos
    0.20
    转åĮĸ
    0.20
    书ä¸Ń
    0.19
    itel
    0.19
    åıijçĶŁåľ¨
    0.19
    åİŁ
    0.19
    Activations Density 0.082%

    No Known Activations