© 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. 10981
    Prev
    Next
    INDEX
    Explanations

    list of items

    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
    ureka
    -0.19
    亲åĪĩ
    -0.19
    ä¸Ģ件
    -0.18
    âĺľ
    -0.18
    è°ħ
    -0.18
    人æĢ§åĮĸ
    -0.18
    çĽĺ
    -0.18
    onical
    -0.18
    æķĸ
    -0.18
    ä»ŀ
    -0.18
    POSITIVE LOGITS
    [Math
    0.18
    _SI
    0.18
    æ®ĭ
    0.18
    åħ¨æĹ¥
    0.18
    èµĦ
    0.18
    æĪIJ人
    0.18
    igue
    0.17
     KG
    0.17
    Platforms
    0.17
    atto
    0.17
    Activations Density 0.001%

    No Known Activations