© 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. 13110
    Prev
    Next
    INDEX
    Explanations

    first time

    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
    çĶľç¾İ
    -0.20
    _utf
    -0.19
    ceased
    -0.18
    ä¸į让
    -0.18
     splash
    -0.18
    oe
    -0.17
     warned
    -0.17
    kı
    -0.17
    æīįè¡Į
    -0.17
     münchen
    -0.17
    POSITIVE LOGITS
    è¿Ļä¹Īå¤ļ
    0.26
    æѤ类
    0.25
    è¿Ļä¹Īä¹ħ
    0.24
     EVER
    0.24
    ä¹Łæĺ¯
    0.23
    以åīį
    0.23
    è¿Ļæł·çļĦ
    0.23
     überhaupt
    0.23
    å¦ĤæѤ
    0.23
     ever
    0.23
    Activations Density 0.073%

    No Known Activations