© 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. 14288
    Prev
    Next
    INDEX
    Explanations

    body parts and actions

    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
    èĪįä¸įå¾Ĺ
    -0.21
    çĶŁæľº
    -0.19
    åĶ¬
    -0.19
    åĿĩ
    -0.19
    æ±¾
    -0.18
    isky
    -0.18
     Lans
    -0.18
    Bush
    -0.18
    vÃŃ
    -0.17
    è¶ĭ
    -0.17
    POSITIVE LOGITS
    åı¹
    0.22
    olib
    0.20
    æĬĵ
    0.19
    xBD
    0.19
    纳åħ¥
    0.19
    rine
    0.18
    é¢ĵ
    0.18
    å·¥ç¨ĭè´¨éĩı
    0.18
     audible
    0.17
    çŃ¾çº¦
    0.17
    Activations Density 0.013%

    No Known Activations