© 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. 13769
    Prev
    Next
    INDEX
    Explanations

    no longer

    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
    缮åīįå·²
    -0.20
     últ
    -0.20
    ä»İæĿ¥æ²¡
    -0.19
    æľĢç»Ī
    -0.19
    åħ¶å®ŀå°±æĺ¯
    -0.19
    åİĨæĿ¥
    -0.19
    ä¸Ģ缴åĪ°
    -0.19
    ä¸Ģè¾ĪåŃIJ
    -0.19
    æĻļæľŁ
    -0.19
    çļĦæľĢåIJİä¸Ģ
    -0.18
    POSITIVE LOGITS
    theless
    0.25
    -than
    0.25
    æĦıä¹īä¸ĬçļĦ
    0.21
    /new
    0.21
    veau
    0.21
    heits
    0.21
    ance
    0.19
    Than
    0.19
    _than
    0.19
    ise
    0.19
    Activations Density 0.011%

    No Known Activations