© 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. 12186
    Prev
    Next
    INDEX
    Explanations

    PGP, Phoenix, Python, Kevin

    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
    LU
    -0.20
    /WebAPI
    -0.19
    åĴĮ个人
    -0.19
    æĬĬèĩªå·±
    -0.18
    ÑĢеÑģÑĤ
    -0.18
    èŀįèµĦ秣èµģ
    -0.18
    人士
    -0.18
     Ñģебе
    -0.18
    åķĨåĬ¡éĥ¨
    -0.18
    unner
    -0.18
    POSITIVE LOGITS
    ATOM
    0.20
     bott
    0.19
     Wade
    0.19
    à¹Ī
    0.19
    enu
    0.19
     Cummings
    0.19
    ign
    0.18
    ů
    0.18
    许
    0.18
    æĹłç©·
    0.18
    Activations Density 0.001%

    No Known Activations