© 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. 13522
    Prev
    Next
    INDEX
    Explanations

    speech context

    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
    çĶŁæ´»ä¹łæĥ¯
    -0.19
    æ±Ĭ
    -0.17
    åľ¨åºĬä¸Ĭ
    -0.16
    stre
    -0.16
    ãģĦãģĨ
    -0.16
    åĮ¹
    -0.15
    ä¹Łä¸įæķ¢
    -0.15
    åģļæ³ķ
    -0.15
    çĿ¬
    -0.15
    ê¹IJ
    -0.15
    POSITIVE LOGITS
    mate
    0.22
    breaker
    0.18
    壮
    0.17
    ero
    0.17
    ical
    0.17
    稿
    0.17
    ALER
    0.15
    fully
    0.15
    room
    0.15
    ioni
    0.15
    Activations Density 0.006%

    No Known Activations