© 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. 14311
    Prev
    Next
    INDEX
    Explanations

    arrested, jail, custody

    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
    sticks
    -0.22
    漫éķ¿çļĦ
    -0.19
    æĽ´éĢĤåIJĪ
    -0.19
     cues
    -0.19
    OMPI
    -0.18
     bleiben
    -0.18
    OLID
    -0.18
    åIJ¬çĿĢ
    -0.17
    uisse
    -0.17
    çłĶ
    -0.17
    POSITIVE LOGITS
    侬
    0.20
    å¼Ģåħ·
    0.19
    _ram
    0.19
    æĪªèĩ³
    0.18
    asic
    0.18
    çŁ¢
    0.18
    cps
    0.18
    gens
    0.18
    zens
    0.18
    etur
    0.18
    Activations Density 0.008%

    No Known Activations