© 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. 12578
    Prev
    Next
    INDEX
    Explanations

    dawn of

    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
    TING
    -0.17
    UCH
    -0.17
    åŀ¢
    -0.16
    å½ĵæŶçļĦ
    -0.16
    аÑģ
    -0.16
    åĢ¾åIJij
    -0.16
    身å¤Ħ
    -0.15
    izzo
    -0.15
    ä¸įèĪį
    -0.15
    æİ·
    -0.15
    POSITIVE LOGITS
    nings
    0.19
    stone
    0.18
    ed
    0.17
    lessly
    0.17
    sWith
    0.17
    ward
    0.17
    licht
    0.17
    ned
    0.16
     ÑĢождениÑı
    0.16
    throp
    0.16
    Activations Density 0.006%

    No Known Activations