© 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. 16893
    Prev
    Next
    INDEX
    Explanations

    Project completion updates

    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
    å½±
    -0.21
     pare
    -0.21
    ace
    -0.21
    æľīéĴĪ对æĢ§
    -0.20
    Rating
    -0.20
    ali
    -0.20
    ald
    -0.19
    and
    -0.19
     qu
    -0.19
    ou
    -0.19
    POSITIVE LOGITS
     miÄĻd
    0.22
     wÅĽ
    0.21
    индивид
    0.20
    индив
    0.19
    å¤ļå°ijéĴ±
    0.19
    åį«
    0.19
    prowadzi
    0.19
    gÅĤÄĻb
    0.18
    szed
    0.18
    theid
    0.18
    Activations Density 0.745%

    No Known Activations