© 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. 11986
    Prev
    Next
    INDEX
    Explanations

    expressing confusion or uncertainty

    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
    ijo
    -0.23
    idget
    -0.23
    ogi
    -0.22
    owering
    -0.20
    ament
    -0.20
    ä¸ĸä¿Ĺ
    -0.20
    erial
    -0.20
    oky
    -0.19
    emes
    -0.19
    eme
    -0.19
    POSITIVE LOGITS
    ç´¢èµĶ
    0.28
    è¿Ļ个éĹ®é¢ĺ
    0.27
    åıijçİ°éĹ®é¢ĺ
    0.25
    è¿Ļç§įæĥħåĨµ
    0.24
    åĽ°æī°
    0.24
    æģIJæħĮ
    0.24
    åıijçİ°äºĨ
    0.23
    çļĦçĹĩçĬ¶
    0.22
    éĢĢè´§
    0.22
    çĹĩçĬ¶
    0.22
    Activations Density 0.337%

    No Known Activations