© 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. 13963
    Prev
    Next
    INDEX
    Explanations

    repair and maintenance updates

    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
    cest
    -0.21
    isObject
    -0.19
     Ade
    -0.19
    å¦Ĥæŀľæĺ¯
    -0.19
    åľ°å½¢
    -0.18
    .scala
    -0.18
    feeding
    -0.18
    æݨå¼Ģ
    -0.18
    ä¸įåıĬ
    -0.18
     next
    -0.17
    POSITIVE LOGITS
    æ¸ħçIJĨ
    0.24
    ä¼ĺåĮĸ
    0.24
    æ¸ħéĻ¤
    0.24
    çŁĽçĽ¾
    0.22
    prm
    0.22
    çĹ¼
    0.22
    åŀĥåľ¾
    0.22
    _decl
    0.21
    èĢģåĮĸ
    0.21
    ä¸ĢéĶ®
    0.21
    Activations Density 0.012%

    No Known Activations