© 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. 12451
    Prev
    Next
    INDEX
    Explanations

    lactase, lactose, lactalbumin

    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
    -0.20
    annes
    -0.19
     пÑĢоведен
    -0.16
    ously
    -0.16
    pee
    -0.16
    åľ¨åIJĮä¸Ģ
    -0.15
    rame
    -0.15
    ellaneous
    -0.15
    è¿ŁåĪ°
    -0.15
    xac
    -0.15
    POSITIVE LOGITS
    acies
    0.18
    ONY
    0.18
    ¼
    0.17
    ally
    0.17
    累累
    0.17
    rix
    0.17
    ivity
    0.17
    eus
    0.17
    åĽ½æĥħ
    0.16
    bling
    0.16
    Activations Density 0.060%

    No Known Activations