© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    police reports

    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
    èĩĬ
    -0.19
     Covenant
    -0.19
     bandwidth
    -0.19
    ä¸į满æĦı
    -0.18
    _snapshot
    -0.17
    rote
    -0.17
    олÑı
    -0.17
    èħ¼
    -0.17
     thoải
    -0.17
    ä¿Ŀè¯ģ
    -0.17
    POSITIVE LOGITS
    æĬ¥æ¡Ī
    0.33
    æįŁå¤±
    0.24
    第äºĮ天
    0.23
     заÑıв
    0.23
    xdc
    0.23
    æIJľæķij
    0.22
    çĦ¦æĢ¥
    0.22
    tmpl
    0.22
     frantic
    0.22
    被éªĹ
    0.22
    Activations Density 0.033%

    No Known Activations