© 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. 14574
    Prev
    Next
    INDEX
    Explanations

    commend actions, professionalism

    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
    åľ°çĭ±
    -0.21
    ä¸įç¡®å®ļ
    -0.20
    .identity
    -0.20
    åĬ¿
    -0.20
    åĿł
    -0.19
    æĶ¶çĽĬ
    -0.19
    æĦŁåıĹ
    -0.19
    HEET
    -0.19
    æĮĤçĿĢ
    -0.18
    åĸľæ¬¢
    -0.18
    POSITIVE LOGITS
     commend
    0.23
    举åĬ¨
    0.23
    è¡Į为
    0.22
     Actions
    0.22
    çļĦè¡Į为
    0.22
    æ¯ħåĬĽ
    0.22
     actions
    0.22
    åģļæ³ķ
    0.21
    表çİ°
    0.21
    .Reporting
    0.20
    Activations Density 0.138%

    No Known Activations