© 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. 11173
    Prev
    Next
    INDEX
    Explanations

    content exists

    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
    å¡
    -0.20
    eid
    -0.20
    NIL
    -0.19
    ä»»ä½ķæŶåĢĻ
    -0.19
    Tumblr
    -0.19
    ç¨ŀ
    -0.19
    pz
    -0.18
    yna
    -0.18
    icol
    -0.18
     antic
    -0.18
    POSITIVE LOGITS
    æĻ®åıĬ
    0.37
    主æµģ
    0.30
    åİĤåķĨ
    0.29
    åķĨçĶ¨
    0.28
    å·²ç»ıæľī
    0.27
    å·²æľī
    0.27
    纷纷
    0.27
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.26
    å·²ç»ıæĺ¯
    0.26
    åºĶçĶ¨
    0.26
    Activations Density 0.079%

    No Known Activations