© 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. 15718
    Prev
    Next
    INDEX
    Explanations

    District Attorney

    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
    OLUTE
    -0.19
    енÑĮ
    -0.18
    æīĭç»Ńè´¹
    -0.17
    å¾ľ
    -0.16
    å¹ħ
    -0.16
    DataMember
    -0.16
     lá»Ļ
    -0.16
    .ActionListener
    -0.16
    è¿ĩæĪ·
    -0.16
    raft
    -0.15
    POSITIVE LOGITS
    æŁ¥çľĭåħ¨æĸĩ
    0.21
    èįĶ
    0.21
    ÊĶ
    0.20
    uber
    0.19
    æ°ı
    0.18
    åºľ
    0.17
    otch
    0.17
    rac
    0.17
    æķı
    0.17
    ENO
    0.17
    Activations Density 0.011%

    No Known Activations