© 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. 15577
    Prev
    Next
    INDEX
    Explanations

    Sent to, finds success, given opportunity, set for

    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
    æݥ轨
    -0.17
    /os
    -0.17
    EGA
    -0.17
     hend
    -0.17
    è¿©
    -0.17
    çļĦè¯Ńè¨Ģ
    -0.17
    Adam
    -0.17
    çĽİ
    -0.17
     holidays
    -0.17
    価
    -0.17
    POSITIVE LOGITS
    éľ¾
    0.21
    ogle
    0.20
     Ãĸnceki
    0.19
    	TokenName
    0.19
    çĹ¿
    0.18
    è´¡çĮ®
    0.18
    èĩªè´¸åĮº
    0.17
    iero
    0.17
    æĪijçľĭ
    0.17
    çķ¶æĤ¨åľ¨
    0.17
    Activations Density 0.020%

    No Known Activations