© 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. 10799
    Prev
    Next
    INDEX
    Explanations

    ombudsman, watchdog, editor, complaint, Defender

    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
    ç»İ
    -0.20
    ä»°
    -0.19
    å®Īä½ı
    -0.18
    æĢ»åħ¬åı¸
    -0.18
     обоÑĢÑĥдование
    -0.18
    æł¹æľ¬
    -0.18
    æĵĴ
    -0.18
    èµ°åĩºåİ»
    -0.18
    å¾Ĺä½ı
    -0.17
    æIJĤ
    -0.17
    POSITIVE LOGITS
     complaints
    0.23
    æĬķè¯ī
    0.23
    æľºæŀĦ
    0.22
    BOR
    0.21
     Complaint
    0.21
    çĶ³è¯ī
    0.20
    ServerError
    0.19
     complaint
    0.18
    .sun
    0.18
    íĶ½
    0.18
    Activations Density 0.006%

    No Known Activations