© 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. 11243
    Prev
    Next
    INDEX
    Explanations

    court for

    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
    .ordinal
    -0.20
    åľ¨å®¶éĩĮ
    -0.19
    shal
    -0.19
    æħ¢æħ¢çļĦ
    -0.19
    kn
    -0.19
    ä¸Ģä¸ĭåŃIJ
    -0.19
    æħ¢æħ¢åľ°
    -0.19
    åİĿ
    -0.19
    æĪijå¦Ī
    -0.19
     gastr
    -0.18
    POSITIVE LOGITS
    anten
    0.21
     Jeg
    0.20
    ä¸ĭè¡Į
    0.20
    Facing
    0.20
    æľī害
    0.19
    ãģĦãģļãĤĮ
    0.19
    两级
    0.19
    综
    0.18
    åīįç½®
    0.18
    _RETRY
    0.18
    Activations Density 0.366%

    No Known Activations