© 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. 15441
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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
    åľºåIJĪ
    -0.20
    ysi
    -0.20
    åľ¨å¤ĸ
    -0.20
    führung
    -0.20
    ahir
    -0.20
    å¨ĥ
    -0.19
    .Notify
    -0.19
    åľ¨åĨħçļĦ
    -0.19
    ä¸ĢçĽ´åľ¨
    -0.18
    ients
    -0.18
    POSITIVE LOGITS
    borg
    0.18
    åħ·ä½ĵ
    0.17
     ×ķ×ij
    0.17
    æĢ§ä»·æ¯Ķ
    0.17
    setCurrent
    0.17
    ç§ĺ书éķ¿
    0.17
    fq
    0.17
    osg
    0.17
    温馨æıIJ示
    0.17
    çİĭåĽ½
    0.16
    Activations Density 0.023%

    No Known Activations