© 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. 15376
    Prev
    Next
    INDEX
    Explanations

    photosynthesis and physiological processes

    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
    âīĤ
    -0.23
    anner
    -0.21
    çĹŀ
    -0.21
    æľį
    -0.20
    è·Łè¿Ľ
    -0.20
     delegate
    -0.20
    PILE
    -0.19
    egin
    -0.19
    otlin
    -0.18
    â´±
    -0.18
    POSITIVE LOGITS
     jsonResponse
    0.23
    åĤ¨å¤ĩ
    0.22
    åħħ足çļĦ
    0.22
     plant
    0.21
    ä½ľçī©
    0.21
    代谢
    0.21
    æ¤įçī©
    0.21
    ì°½
    0.21
     interior
    0.20
    qr
    0.20
    Activations Density 0.150%

    No Known Activations