© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    associated with / containing

    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
    æ°ijéĹ´
    -0.20
    çļĦ第ä¸Ģ个
    -0.19
    .ak
    -0.19
    åį´åıĪ
    -0.19
    oman
    -0.18
     Cedar
    -0.18
    	Dictionary
    -0.17
    etter
    -0.17
    discard
    -0.17
    _Reference
    -0.17
    POSITIVE LOGITS
     thereof
    0.66
     therein
    0.46
    éļıä¹ĭ
    0.42
     accordingly
    0.39
    çĶ±æѤ
    0.38
    缸åºĶ
    0.37
    ãģĿãĤĮãģ«
    0.37
     associated
    0.34
    缸åºĶçļĦ
    0.34
     deren
    0.32
    Activations Density 0.360%

    No Known Activations