© 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. 12635
    Prev
    Next
    INDEX
    Explanations

    umlaut vowels in German

    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
     or
    -0.22
    ÑĥлÑĮÑĤ
    -0.22
     this
    -0.21
     otherwise
    -0.21
     cu
    -0.21
     зав
    -0.21
    -0.21
     еÑģÑĤÑĮ
    -0.21
     that
    -0.21
    schütz
    -0.21
    POSITIVE LOGITS
     пÑĢиÑıÑĤн
    0.39
    индивид
    0.36
     nuest
    0.34
    ÓĽ
    0.33
    ÑĩÑĢежден
    0.33
    индив
    0.33
    íĹĢ
    0.32
     vÃŃde
    0.32
    iéndo
    0.31
    наÑĨионалÑĮн
    0.31
    Activations Density 0.793%

    No Known Activations