© 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. 11555
    Prev
    Next
    INDEX
    Explanations

    Team Kodi, team marks, team competitions

    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
    æĪĺåľºä¸Ĭ
    -0.18
     tract
    -0.16
    å±Ģéķ¿
    -0.16
    æĤłæĤł
    -0.16
    ãģ¾ãģ¾
    -0.15
    gil
    -0.15
    èµĽåľº
    -0.15
    ances
    -0.15
    åľ°çIJĥä¸Ĭ
    -0.15
    è¹Ĭ
    -0.15
    POSITIVE LOGITS
    perature
    0.29
    atic
    0.23
    amen
    0.21
    åĴĮ个人
    0.20
    atical
    0.18
    åĵ¡
    0.18
     ngũ
    0.17
    atics
    0.17
    atically
    0.17
    ä¸ĬçļĦ
    0.17
    Activations Density 0.049%

    No Known Activations