© 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. 12241
    Prev
    Next
    INDEX
    Explanations

    black hole

    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
    estic
    -0.21
    atism
    -0.20
    åĹij
    -0.19
    èĪ
    -0.19
    illon
    -0.18
    åı©
    -0.18
    æĹłåģ¿
    -0.18
    arger
    -0.17
    æīİæł¹
    -0.17
    rome
    -0.17
    POSITIVE LOGITS
    ium
    0.19
    wat
    0.19
     lum
    0.19
     sco
    0.19
    ä¸įæŃ»
    0.19
     locally
    0.18
    æĬ¢æķij
    0.18
    æĺİçıł
    0.18
    ä¸ĵé¢ĺ
    0.18
     replica
    0.18
    Activations Density 0.002%

    No Known Activations