© 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. 13842
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĽ´æ·±
    -0.17
    esson
    -0.17
    /filepath
    -0.17
    IRM
    -0.16
    ãĬĻ
    -0.16
    ény
    -0.16
    ifen
    -0.16
     cref
    -0.16
    ecer
    -0.16
    reibung
    -0.16
    POSITIVE LOGITS
    0.21
    ol
    0.20
    manship
    0.20
    matic
    0.20
     colors
    0.18
    fully
    0.18
    å®Ŀå®Ŀ
    0.18
    çķĮçļĦ
    0.18
    lets
    0.18
     liqu
    0.17
    Activations Density 0.000%

    No Known Activations