© 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. 14892
    Prev
    Next
    INDEX
    Explanations

    reduction of costs and speed

    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
    à¸Ńร
    -0.17
    çī¹åĪ«å£°æĺİ
    -0.17
    åİŁæľ¬
    -0.17
    æĸ¹åľĨ
    -0.17
    æľ¬èº«çļĦ
    -0.17
    LY
    -0.17
    çĮĸ
    -0.16
    leh
    -0.16
    curity
    -0.16
    ëį°
    -0.16
    POSITIVE LOGITS
    sWith
    0.22
    erator
    0.21
    ness
    0.21
    naire
    0.21
    æݪæĸ½
    0.21
    ize
    0.20
    teen
    0.20
    ting
    0.20
    ree
    0.19
    swith
    0.19
    Activations Density 0.007%

    No Known Activations