© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15196
    Prev
    Next
    INDEX
    Explanations

    adrenergic, renal, amines, phrine

    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
    çŁ³å¤´
    -0.22
    æ³¥åľŁ
    -0.20
    骨头
    -0.20
    水稻
    -0.20
    åıĮåıĮ
    -0.19
    rice
    -0.19
    ç¬ijèĦ¸
    -0.19
    éĴµ
    -0.18
    GRID
    -0.18
    çªŁ
    -0.18
    POSITIVE LOGITS
    æ£ķèī²
    0.21
    æĸ°åįİ
    0.20
    brown
    0.19
    è¡Ģåİĭ
    0.19
    é»Ħå±±
    0.19
    ÑĩеÑĢ
    0.18
     forests
    0.18
    xes
    0.18
    è±¹
    0.18
     Pent
    0.18
    Activations Density 0.175%

    No Known Activations