© 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. 15532
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by particles

    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
    主è§Ĥ
    -0.21
    åĪ·
    -0.21
    lime
    -0.20
     subjective
    -0.20
     prelim
    -0.20
    irmed
    -0.19
     yay
    -0.19
    _principal
    -0.19
    -net
    -0.18
    ricks
    -0.18
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.21
    æĤ²åĵĢ
    0.21
    æľīèī²
    0.20
    æIJ¬
    0.20
    禾
    0.19
    fol
    0.19
    åħ¨å¥Ĺ
    0.18
    าม
    0.18
     somewhere
    0.18
    unes
    0.18
    Activations Density 0.080%

    No Known Activations