© 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. 13474
    Prev
    Next
    INDEX
    Explanations

    fruits and melons

    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
     Bison
    -0.23
    çĩĥ
    -0.21
     Brew
    -0.20
    ODB
    -0.20
     bếp
    -0.20
     Herb
    -0.20
    é£ŁåłĤ
    -0.19
     verst
    -0.19
    åĪ·
    -0.19
     Stockholm
    -0.19
    POSITIVE LOGITS
    åĵģç§į
    0.35
    apple
    0.29
    fruit
    0.29
     fruit
    0.28
     varieties
    0.28
    æ°´æŀľ
    0.28
     fruits
    0.27
    æŀľå®ŀ
    0.27
    APPLE
    0.26
    çĶľç¾İ
    0.24
    Activations Density 0.049%

    No Known Activations