© 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. 11611
    Prev
    Next
    INDEX
    Explanations

    512x512

    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
    risk
    -0.20
    uate
    -0.19
    ocus
    -0.18
    nf
    -0.18
    élé
    -0.18
    ousse
    -0.18
    afil
    -0.17
    æįİ
    -0.17
    çļĦæĪIJ绩
    -0.17
    strand
    -0.17
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.22
    åIJ¼
    0.17
    ãĥĢãĥ³
    0.17
    anim
    0.17
     Bald
    0.17
    å¶Ĥ
    0.17
    æīĵå¼Ģ
    0.17
     memory
    0.17
    寤
    0.17
    ãĤ«
    0.16
    Activations Density 0.057%

    No Known Activations