© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11441
    Prev
    Next
    INDEX
    Explanations

    areas or regions

    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
    å½¼æѤ
    -0.20
    URI
    -0.18
     thumb
    -0.18
    çĪ·
    -0.18
    esz
    -0.17
    æľĢè¿ij
    -0.17
    æŃ£å¦Ĥ
    -0.17
    æ¯Ķå¦Ĥ
    -0.17
    %/
    -0.17
    eld
    -0.17
    POSITIVE LOGITS
     newcom
    0.20
    亲åıĭ
    0.20
    æļ¨
    0.19
    åı¯çĪ±çļĦ
    0.19
    (optional
    0.18
    ä¸Ńå¼ı
    0.18
    ãĢĭï¼Į
    0.18
    ä¸Ģçľĭ
    0.18
     Ups
    0.18
    åĬ¡å®ŀ
    0.18
    Activations Density 0.239%

    No Known Activations