© 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. 14891
    Prev
    Next
    INDEX
    Explanations

    warranty

    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
    lo
    -0.21
    loh
    -0.20
    ãĢħ
    -0.20
    ended
    -0.19
    amed
    -0.17
    est
    -0.17
    _ACC
    -0.17
     medi
    -0.17
    ested
    -0.17
    icted
    -0.17
    POSITIVE LOGITS
    æľŁåĨħ
    0.28
    åĪ°æľŁ
    0.23
    æľŁ
    0.21
    æľŁéĻIJ
    0.19
    åĪĩãĤĮ
    0.19
    é½ģ
    0.19
    çIJĽ
    0.18
    oes
    0.17
    ihan
    0.17
    æĹłç©·
    0.17
    Activations Density 0.017%

    No Known Activations