© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    death and identification

    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
     köln
    -0.20
    åIJįæ°Ķ
    -0.19
    ä¸įçŁ¥ä¸įè§ī
    -0.19
     salopes
    -0.19
     зай
    -0.19
     luder
    -0.19
     Ging
    -0.19
    ://{
    -0.19
    FRING
    -0.18
     cá»ķ
    -0.18
    POSITIVE LOGITS
    å°¸ä½ĵ
    0.29
     death
    0.28
    æŃ»äº¡
    0.27
    éī´å®ļ
    0.26
    人ä½ĵ
    0.25
    death
    0.25
    æŃ»èĢħ
    0.24
     crem
    0.24
    å±į
    0.24
    æ®ĵ
    0.24
    Activations Density 0.019%

    No Known Activations