© 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. 13320
    Prev
    Next
    INDEX
    Explanations

    ranks and titles

    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
    交èŀį
    -0.19
    èĦĤ
    -0.19
    (Action
    -0.19
    è¡·
    -0.18
    iosa
    -0.18
    unes
    -0.18
     Brad
    -0.18
     Barth
    -0.18
     mix
    -0.17
    ?action
    -0.17
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.31
    级
    0.28
    -level
    0.28
    å¢ĥçķĮ
    0.26
    级åĪ«
    0.26
    éĹ¨æ§Ľ
    0.25
    -Level
    0.23
    ç´ļ
    0.23
    éĺ¶æ®µ
    0.23
    -status
    0.22
    Activations Density 0.067%

    No Known Activations