© 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. 15589
    Prev
    Next
    INDEX
    Explanations

    murder, assault, and related crimes

    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
    æ·«
    -0.19
    ä¹łè¿ij
    -0.19
     rut
    -0.18
     afterEach
    -0.18
    etz
    -0.18
    aste
    -0.17
    ryn
    -0.17
    orp
    -0.17
    ä¹IJæĦı
    -0.17
    nice
    -0.17
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.25
    æŃ»èĢħ
    0.22
    çĶŁåij½
    0.20
    åĶ¯ä¸Ģ
    0.20
    SMART
    0.20
    责任人
    0.19
    çļĦçĶŁåij½
    0.18
    çĶŁåij½çļĦ
    0.18
    ä¸Ģæłĭ
    0.18
    åĶ¯ä¸ĢçļĦ
    0.18
    Activations Density 0.013%

    No Known Activations