© 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. 14016
    Prev
    Next
    INDEX
    Explanations

    planning and committing 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
     expelled
    -0.21
    å¼·ãģı
    -0.20
    æĦŁåıĹ
    -0.20
    æµģ失
    -0.20
    åĵŃäºĨ
    -0.19
    ä¸Ģç¢Ĺ
    -0.19
    è°Īèµ·
    -0.19
     ÑĢаÑģÑħод
    -0.18
    æĢı
    -0.18
    飨
    -0.18
    POSITIVE LOGITS
     planned
    0.28
    计åĪĴ
    0.26
    æĪIJåĬŁçİĩ
    0.24
    çĺ«
    0.23
     Planned
    0.23
    æĪIJåĬŁ
    0.22
    è¡ĮåĬ¨
    0.21
    è¨ĪåĬĥ
    0.21
     operation
    0.20
    éĢł
    0.20
    Activations Density 0.056%

    No Known Activations