© 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. 13736
    Prev
    Next
    INDEX
    Explanations

    to verb

    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
    å¹´èĸª
    -0.23
    declaration
    -0.20
    ä¸įåĥħ
    -0.19
    åıĪ称
    -0.19
    loggedin
    -0.19
    çŀŃ解並
    -0.19
    æĶ¾å¼ĥäºĨ
    -0.19
    suppress
    -0.19
    åĪĿè¡·
    -0.18
    çķĮçļĦ
    -0.18
    POSITIVE LOGITS
    çĶ±æѤ
    0.23
    _strerror
    0.22
    缸åºĶçļĦ
    0.21
     willen
    0.20
     ê·¸ê²ĥìĿĦ
    0.20
     thereof
    0.20
    使ä¹ĭ
    0.20
     ultimately
    0.20
     honest
    0.20
    á»Ķ
    0.20
    Activations Density 0.245%

    No Known Activations