© 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. 15302
    Prev
    Next
    INDEX
    Explanations

    giant

    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
    ãģĦãģĨ
    -0.18
    好åĿı
    -0.18
    itional
    -0.17
    hora
    -0.16
    è£Ķ
    -0.16
    yer
    -0.16
    iences
    -0.16
    ãģ£ãģįãĤĬ
    -0.15
    ders
    -0.15
    INGTON
    -0.15
    POSITIVE LOGITS
    们éĥ½
    0.31
    们çļĦ
    0.29
    们
    0.23
    æĹłæ¯Ķ
    0.22
    åĢij
    0.22
    esses
    0.22
    -hearted
    0.21
    -sized
    0.21
    -scale
    0.20
    emente
    0.20
    Activations Density 0.013%

    No Known Activations