© 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. 13454
    Prev
    Next
    INDEX
    Explanations

    words in other languages

    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
    èĢ¸
    -0.20
     skys
    -0.20
    大åݦ
    -0.19
    çī¦
    -0.19
    ì¼Ģ
    -0.19
     marathon
    -0.19
     ÙĬÙĪس
    -0.19
     India
    -0.19
    å§Ŀ
    -0.18
     passphrase
    -0.18
    POSITIVE LOGITS
    æµģåĬ¨æĢ§
    0.25
    благо
    0.23
    åIJĪæ³ķæĢ§
    0.23
    è¢į
    0.23
    OKIE
    0.22
    индивид
    0.22
    ÑĩÑĢ
    0.22
    åľ¨å½ĵåľ°
    0.22
    ç»ıèIJ¥èĢħ
    0.21
    å½ĵåľ°äºº
    0.21
    Activations Density 0.015%

    No Known Activations